concept
active
concept:internality-criterion

Internality Criterion

Criterion requiring that causal influence of internal state on description be internal, not routed through sampled outputs; rules out pseudo-introspection via self-observation.

Neighborhood — ranked by edge-count

Findings (2)

finding
  • Models can detect and identify injected concept vectors ~20% of the time at optimal layer/strength in Opus 4.1, with immediacy suggesting internal rather than output-inferred detection.
  • Models can distinguish artificially prefilled outputs from intentional responses by referencing prior internal representations; injection of matching concept vector causes model to retroactively accept prefill as intentional.

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.