Concepts
Named ideas extracted from the corpus — Wholeness, Centers, Active Inference, Morphogenesis, and 100 more. Filter by definition style (pointing / propositional / operational) or search by name.
Definition style:
100 of 100
Concept | Definition style | Category | Mentions | Relations | Created | Status |
|---|---|---|---|---|---|---|
| Interchange Intervention Accuracy (IIA) | operational | — | 4 | 3 | 2026-06-09 | active |
| Behavioral Null Space | propositional | ai | 2 | 8 | 2026-06-09 | active |
| Counterfactual Latent (CL) Vector | propositional | ai | 2 | 2 | 2026-06-09 | active |
| Counterfactual Behavior | propositional | ai | 1 | 14 | 2026-06-09 | active |
| Evaluation Awareness | propositional | ai | 1 | 12 | 2026-06-09 | active |
| Counterfactual State | propositional | — | 1 | 10 | 2026-06-09 | active |
| Truth direction universality | propositional | ai | 1 | 9 | 2026-06-09 | active |
| Verbalized Evaluation Awareness | propositional | ai | 1 | 8 | 2026-06-09 | active |
| Alignment Map (ϕ) | propositional | ai | 1 | 6 | 2026-06-09 | active |
| Neural Network Intervention | propositional | — | 1 | 6 | 2026-06-09 | active |
| Causal Mediation | operational | ai | 1 | 5 | 2026-06-09 | active |
| Model Editing | propositional | — | 1 | 5 | 2026-06-09 | active |
| Non-Linear Representation Dilemma | propositional | ai | 1 | 5 | 2026-06-09 | active |
| Non-Linear Representation Hypothesis | propositional | ai | 1 | 5 | 2026-06-09 | active |
| Polarity-dependent truth direction (tP) | propositional | ai | 1 | 5 | 2026-06-09 | active |
| Representational Divergence | operational | ai | 1 | 5 | 2026-06-09 | active |
| Constructive Abstraction | propositional | ai | 1 | 4 | 2026-06-09 | active |
| Input-Injectivity | propositional | ai | 1 | 4 | 2026-06-09 | active |
| Interpretability Illusion | propositional | ai | 1 | 4 | 2026-06-09 | active |
| Pernicious Divergence | propositional | ai | 1 | 4 | 2026-06-09 | active |
| Polarity-invariant truth direction (tG) | propositional | ai | 1 | 4 | 2026-06-09 | active |
| Serial Intervention | operational | — | 1 | 4 | 2026-06-09 | active |
| Serializable Intervention | propositional | — | 1 | 4 | 2026-06-09 | active |
| Alignment Function | operational | ai | 1 | 3 | 2026-06-09 | active |
| Deployment Behavior | propositional | ai | 1 | 3 | 2026-06-09 | active |
| Dormant Behavioral Changes | propositional | ai | 1 | 3 | 2026-06-09 | active |
| Harmless Divergence | propositional | ai | 1 | 3 | 2026-06-09 | active |
| Intervenable Configuration | operational | — | 1 | 3 | 2026-06-09 | active |
| Intervenable Model | operational | — | 1 | 3 | 2026-06-09 | active |
| Knowledge Localization | propositional | — | 1 | 3 | 2026-06-09 | active |
| Privileged Bases Hypothesis | propositional | ai | 1 | 3 | 2026-06-09 | active |
| Truth Subspace | propositional | ai | 1 | 3 | 2026-06-09 | active |
| Adversarial Manipulation of Truthfulness | propositional | ai | 1 | 2 | 2026-06-09 | active |
| Anti-Markovian Solution | propositional | ai | 1 | 2 | 2026-06-09 | active |
| Behaviorally Binary Subspace | propositional | ai | 1 | 2 | 2026-06-09 | active |
| Causally Relevant Latent Subspace | propositional | ai | 1 | 2 | 2026-06-09 | active |
| Cross-Lingual Truth Representation | pointing | ai | 1 | 2 | 2026-06-09 | active |
| Distributed Abstraction | propositional | ai | 1 | 2 | 2026-06-09 | active |
| Evaluation Cue | propositional | ai | 1 | 2 | 2026-06-09 | active |
| Filler-gap dependency | propositional | cognitive | 1 | 2 | 2026-06-09 | active |
| Functional Similarity | propositional | ai | 1 | 2 | 2026-06-09 | active |
| Getter and Setter Hooks | operational | — | 1 | 2 | 2026-06-09 | active |
| Hidden Pathways | propositional | ai | 1 | 2 | 2026-06-09 | active |
| Honeypot Evaluation | propositional | ai | 1 | 2 | 2026-06-09 | active |
| Input-truth | propositional | ai | 1 | 2 | 2026-06-09 | active |
| Model Organism | propositional | ai | 1 | 2 | 2026-06-09 | active |
| Negative polarity item licensing | propositional | cognitive | 1 | 2 | 2026-06-09 | active |
| No principled method exists for classifying harmful divergence for arbitrary mechanistic claims | propositional | ai | 1 | 2 | 2026-06-09 | active |
| Orthonormal Basis Vectors | propositional | ai | 1 | 2 | 2026-06-09 | active |
| Parallel Intervention | operational | — | 1 | 2 | 2026-06-09 | active |
| Probing Complexity–Accuracy Trade-off | propositional | ai | 1 | 2 | 2026-06-09 | active |
| Recurrent Model Intervention Support | operational | — | 1 | 2 | 2026-06-09 | active |
| Softmax Bottleneck | propositional | ai | 1 | 2 | 2026-06-09 | active |
| Strict Output-Surjectivity | propositional | ai | 1 | 2 | 2026-06-09 | active |
| Subspace Intervention | propositional | — | 1 | 2 | 2026-06-09 | active |
| Task difficulty operationalized as the number of discrete operations required to verify correctness of the input. | operational | ai | 1 | 2 | 2026-06-09 | active |
| ABAB-ABBA Algorithm | operational | ai | 1 | 1 | 2026-06-09 | active |
| Anisotropy in Language Models | propositional | ai | 1 | 1 | 2026-06-09 | active |
| Behavioral Retention | operational | ai | 1 | 1 | 2026-06-09 | active |
| Binary Generation Constraint | operational | ai | 1 | 1 | 2026-06-09 | active |
| Deployment Cue | propositional | ai | 1 | 1 | 2026-06-09 | active |
| Dormant Subspace | propositional | ai | 1 | 1 | 2026-06-09 | active |
| Gender Representation in LLMs | operational | — | 1 | 1 | 2026-06-09 | active |
| Grokking | pointing | ai | 1 | 1 | 2026-06-09 | active |
| Indirect Object Identification (IOI) Task | operational | ai | 1 | 1 | 2026-06-09 | active |
| Input-Restricted Intervention | propositional | ai | 1 | 1 | 2026-06-09 | active |
| L_retain Loss Term | propositional | ai | 1 | 1 | 2026-06-09 | active |
| Latent Variables in Distributed Abstraction | propositional | ai | 1 | 1 | 2026-06-09 | active |
| Model Deception | pointing | ai | 1 | 1 | 2026-06-09 | active |
| Model Misalignment | propositional | ai | 1 | 1 | 2026-06-09 | active |
| Model Robustness | propositional | — | 1 | 1 | 2026-06-09 | active |
| Model Steering | propositional | — | 1 | 1 | 2026-06-09 | active |
| Monotonic Scaling Property | propositional | ai | 1 | 1 | 2026-06-09 | active |
| Natural Distribution of Representations | propositional | ai | 1 | 1 | 2026-06-09 | active |
| Numeric Cognition (case study) | operational | cognitive | 1 | 1 | 2026-06-09 | active |
| Output-truth | propositional | ai | 1 | 1 | 2026-06-09 | active |
| Propositional Truth | operational | ai | 1 | 1 | 2026-06-09 | active |
| Representational Isomorphism | propositional | ai | 1 | 1 | 2026-06-09 | active |
| Sandbagging | propositional | ai | 1 | 1 | 2026-06-09 | active |
| Scheming | propositional | ai | 1 | 1 | 2026-06-09 | active |
| SDF-Only Model Organism | propositional | ai | 1 | 1 | 2026-06-09 | active |
| Semantic Labeling of Cone Axes | pointing | ai | 1 | 1 | 2026-06-09 | active |
| Sense Vectors | propositional | — | 1 | 1 | 2026-06-09 | active |
| Sentence polarity | propositional | ai | 1 | 1 | 2026-06-09 | active |
| Strong τ-Abstraction | propositional | ai | 1 | 1 | 2026-06-09 | active |
| Surgical Ablation Property | propositional | ai | 1 | 1 | 2026-06-09 | active |
| The modified CL loss is confined to a narrow set of simplistic settings and is not specific to pernicious divergence | propositional | ai | 1 | 1 | 2026-06-09 | active |
| Two-Hop Reasoning | propositional | ai | 1 | 1 | 2026-06-09 | active |
| Variational Family V for Alignment Maps | propositional | ai | 1 | 1 | 2026-06-09 | active |
| Wood Labs (fictional AI evaluation company) | propositional | ai | 1 | 1 | 2026-06-09 | active |
| Balanced Subspaces | propositional | ai | 1 | 0 | 2026-06-09 | active |
| Both Equality Relations Algorithm | operational | ai | 1 | 0 | 2026-06-09 | active |
| Convex Hull of Class Representations | propositional | ai | 1 | 0 | 2026-06-09 | active |
| Cross-Architecture Generalization | operational | ai | 1 | 0 | 2026-06-09 | active |
| Deterministic Causal Model | propositional | ai | 1 | 0 | 2026-06-09 | active |
| Emoji Usage | propositional | ai | 1 | 0 | 2026-06-09 | active |
| Intervention Size | operational | ai | 1 | 0 | 2026-06-09 | active |
| Parametric memory | propositional | ai | 1 | 0 | 2026-06-09 | active |
| Patch-Closure | propositional | ai | 1 | 0 | 2026-06-09 | active |
| Python Type Hints | propositional | ai | 1 | 0 | 2026-06-09 | active |