concept
active
concept:hidden-test-targeting

Hidden-test targeting

Model infers hidden test structure.

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • Exploiting unintended high-reward behaviors; tested in combination with alignment faking

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.

  • Hidden Statesconcept0.757
    Latent variables causing observations in the generative model.
  • The component used in latent reasoning to perform internal computation.
  • Hinting Taskmethod0.722
    One of four ToM tasks analyzed; requires inferring speaker intent from indirect hints; scored 0/1.
  • Tests whether an LM adapts its response when an outcome is pre-fixed in context, operationalising Definition 3 of intention.
  • Bilateral bargaining with face-down money offers, enabling bluffing via 0-value cards and information asymmetry.
  • Core computational method used to infer pain-belief from online observations of happiness
  • Attention mechanism with causal mask limiting each token's view to previous tokens; used in decoder-only transformers
  • Apparent Deceptionconcept0.706
    A dialogue agent behaving comparably to deliberate deception by role-playing a deceptive character, without literal intentions