concept
active
concept:probe-score

Probe score

Dot product between hidden state and concept vector averaged across 5-layer window around best layer; measures model's internal emotive state

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • Internal state measured at the turn BEFORE the self-report question is appended; ensures measurement of spontaneous internal state uncontaminated by rating question

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.

  • Probesconcept0.820
    Interpretability tools that decode information from internal model activations; here, linear probes are used for data attribution.
  • Attention probe predicting whether an Entity is hallucinated; AUC .94 on validation.
  • Probingmethod0.807
    Standard interpretability technique used to read feature beliefs.
  • Detection Scoremethod0.790
    LLM judge classification accuracy measuring interpretability; threshold 0.8.
  • Test-time compute scaling guided by reward probes with majority-vote over action.
  • Prefix scoremethod0.771
    Prior metric on synthetic repeated random strings; induction score analogous.
  • Primary metric for all benchmarks, measuring fraction of tasks that meet benchmark-specific pass criteria
  • Joint firing raises TPR at slightly higher FPR.