framework
active
framework:trait-activation-theoryTrait Activation Theory
Theory used to justify activating only the trait cued by the current prompt, avoiding cross-trait interference
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (1)
method
- Agent-Based Decision ModuleimplementsModule that dynamically selects which facet-level CVs to inject based on contextual cues in the current prompt
Frameworks (1)
framework
- The primary novel framework introduced in the paper for learning facet-level personality control vectors
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.
- Pearson correlation of feature activations across 40M tokens used to measure feature similarity and universality across models
- Assumption that small anchor changes can produce sharp performance shifts when conditions are favorable.
- Traditional mechanistic accounts (Danto, Chisholm, Goldman) that Juarrero critiques as resting on outdated Newtonian causality.
- Component of the contrastive retrieval pipeline analyzing activation statistics.
- Mechanism by which activation of an emotion feature sometimes leads to later suppression of that same featurequestion0.725Identified research gap: the paper observes anti-persistence but has no explanation for it
- The standard evolutionary framework based on selective advantage of step-wise mutations, which Alexander argues is insufficient alone to explain global geometric order in organisms
- Studies how inputs are gated in attention, cited as analogy.
- Internal representations of the model on which probes operate; the method uses activations to rank datapoints.