concept
active
concept:thought-detection

thought detection

Task of detecting a model's internal thoughts; found by Lindsey (2026) to peak at ~2/3 depth in transformers.

Neighborhood — ranked by edge-count

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

  • Monitoring reasoning traces for misbehavior.
  • Detection Scoremethod0.771
    LLM judge classification accuracy measuring interpretability; threshold 0.8.
  • Thinking stepsconcept0.771
    Segments of reasoning separated by \n\n tokens used as the unit of analysis in ReflCtrl
  • William James aphorism cited by Levin to support the idea that thought forms possess minimal agency rather than being purely passive data.
  • Task where the model must simultaneously identify an injected thought and transcribe a text sentence.
  • Experimental paradigm where the model is told about the possibility of thought injection and asked to report detection and identification.
  • Task paradigm from prior work asking 'Did you detect an injected thought?' via YES/NO logit comparison; shown here to be confounded