Recognition of self-generated outputs

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Predictive Coding Account of Self-Recognitionconcept0.755
  Apps and Tsakiris's proposal that self-recognition can be modeled probabilistically under the free energy principle
• Intrinsic Self-Correction via Linear Representationsframework0.754
  Framework by Lee et al. explaining self-correction via linear latent concept directions, closely related prior work.
• Self-Referencing Activationsconcept0.751
  Latent model activations when processing inputs framed from the model's own perspective
• Self-Referential Processingconcept0.746
  The central experimental manipulation: directing a model to attend to its own cognitive activity
• Identification of algorithms implemented in attention layers, distributed across attention headsfinding0.743
  VPD successfully recovered interpretable attention algorithms (previous-token behavior, syntax-boundary routing) in weight space without requiring manual decomposition across heads.
• Detecting Unintended Outputs via Introspectionfinding0.739
  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.
• Sampled-decoding self-reportmethod0.738
  Temperature=0.8 sampled decoding for self-report; reduces collapse moderately but remains discrete and noisy
• Self-reportconcept0.738
  The model's verbal description of its internal state, which may be accurate or confabulated.