concept
active
concept:privileged-accessPrivileged access
Information about own internal state available only to the model.
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (1)
method
- Standard test from Binder et al. comparing self and cross predictors.
Concepts (1)
concept
- Privileged self-accessrelated_toModels 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 edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- 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
- 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.
- 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.