concept
active
concept:causal-self-explanationCausal self-explanation
Model explains its own behavior without implying introspection.
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (1)
method
- Training models to answer Yes/No whether a prompt edit changes their behavior.
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.
- A framework the paper uses alongside feature geometry to deepen mechanistic understanding of LMs
- Function determining the value of a variable based on its causal parents in an acyclic causal model.
- Mechanistic interpretability technique for locating factual associations, mentioned as future work direction.
- Core concept: degree to which an agent exerts unique predictive power on its future; key to cognition at all scales.
- The structural-realist grounding for self-evidencing after the bounded self is relinquished.
- Whether an internal direction causally controls a target behavior, verified by intervention success
- The formal method used to establish that the identified circuit causally mediates the model's cyclic reasoning behavior
- Property that causal mechanisms remain stable across environments; desirable for OOD.