concept
active
concept:privileged-access

Privileged access

Information about own internal state available only to the model.

Neighborhood — ranked by edge-count

Methods (1)

method

Concepts (1)

concept
  • Models predict their own hypothetical behavior better than other models can, demonstrating a form of privileged self-access per Binder et al. 2024

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.

  • Privileged Basisconcept0.825
    A property of activations where neural network features align with basis dimensions due to sparse activation functions; absent in the residual stream but present in tokens, attention patterns, and MLP activations
  • The capacity to detect and report one's own internal states, measured via the five-adjective task and paradox reflection
  • Privacyconcept0.751
  • authorityconcept0.747
    The condition that a speaker has the right to issue an order or promise, especially for purchase orders.
  • Possible explanations for difference from Li et al.
  • Attentionconcept0.732
    Selective attention mechanism is a component of GWT-2 indicator; AST-1 models and enables control over attention
  • Hypothesis that neurons form privileged bases to encode information; consistent with constructive abstraction
  • Information available for reasoning, report, and decision-making.