concept
active
concept:counterfactual-behaviorCounterfactual Behavior
The behavior that would have occurred had the value of a causal variable been different while everything else remained the same; used as training labels in DAS/MAS.
Neighborhood — ranked by edge-count
Thinkers (1)
thinker
- Judea PearlstudiesDeveloped causal graph models and the do-operator, foundational to modern causal inference.
Methods (1)
method
- Interchange InterventionimplementsFundamental operation for causal abstraction analysis; forces neurons to take values from source inputs to create counterfactuals.
Concepts (6)
concept
- Counterfactualrelated_toThe output value a model produces when an interchange intervention forces certain variables to take values from source inputs.
- Counterfactual Hypothesisrelated_toAbility to entertain competing hypotheses within one inference engine; proposed hallmark of mindful inference
- Counterfactual Staterelated_toThe state a neural network is placed in when its activations are modified via intervention
- Counterfactual Thinkingrelated_toEncoding possible future or alternative states; bioelectric patterns can represent an alternative morphological target even in an intact animal.
- Counterfactual maintenancerelated_toThe mental effort of holding models of how things could/should be different from actuality, contributing to compression stress.
- Counterfactual Representationrelated_to
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Lens for evaluating explanations by whether they help predict behavior on counterfactual inputs.
- True/false claims that a prompt edit shifts a behavior rate by at least 30pp; basis for all evaluation labels.
- Training models to answer Yes/No whether a prompt edit changes their behavior.
- Fine-tuning on reflection turns to implant principles into workspace.
- Computes feature attribution passing ablated pre-activation through JumpReLU to handle inhibition.
- Pre-recorded latent vector encoding the expected causal variable values post-intervention; used as ground truth in the CLMAS auxiliary loss.
- Auxiliary training objective from Grant (2025) that constrains intervened representations to remain near natural distribution
- World-disclosing behavior that resolves uncertainty; driven by epistemic value and novelty components of expected free energy