claim
active
claim:counterfactual-investigation-is-a-broadly-applicable-tool-for-studying-deployed-modelsCounterfactual investigation is a broadly applicable tool for studying deployed models
Pipeline retargetable to other behavior classes.
Source paper
extracted_from(2026) · Adam Karvonen · Euan Ong · Subhash Kantamneni · Samuel Marks
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (1)
finding
- In- and out-of-distribution generalization.
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.
- Ability to entertain competing hypotheses within one inference engine; proposed hallmark of mindful inference
- Encoding possible future or alternative states; bioelectric patterns can represent an alternative morphological target even in an intact animal.
- Acknowledged limitation.
- The mental effort of holding models of how things could/should be different from actuality, contributing to compression stress.
- True/false claims that a prompt edit shifts a behavior rate by at least 30pp; basis for all evaluation labels.
- Lens for evaluating explanations by whether they help predict behavior on counterfactual inputs.
- The output value a model produces when an interchange intervention forces certain variables to take values from source inputs.