Interpretability findings can validate or invalidate what AI systems claim about their own experience.

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

• AI self-reports about experience constitute valid empirical data even without proving consciousness.claim0.810
• We hypothesize that interpretability methods could provide further evidence about indicators in particular systems or serve as the basis for distinct tests for consciousness.hypothesis0.809
  Forward-looking suggestion for how inner interpretability could extend the indicator method
• Activation-based interpretability does not immediately explain the computations that gave rise to activations; understanding parameters is necessary for deeper insightclaim0.781
  Motivates shift from studying model activations ('thoughts') to understanding parameters ('the computations themselves').
• The field of interpretability has focused mainly on understanding model activations, not the computations themselvesclaim0.778
  Motivation for VPD's parameter-focused approach.
• In the case of AI, inferences from behavior to features of internal processes are often unreliable, as demonstrated by recent LLMs.claim0.777
  Justifies using internal indicators rather than behavioral tests for AI consciousness
• Interpretable predictions can help resolve variants of uncertain significanceclaim0.777
  Motivating claim that mechanistic explanations add clinical value for VUS.
• An artificial model replicating mechanisms of self-illusion can test hypotheses and reveal novel affordances for non-human intelligence.hypothesis0.771
  Methodological proposal to integrate knowledge from contemplative and cognitive science into AI/artificial life frameworks.
• Interpretability tools can reveal what 'feeling alive' looks like inside a neural network model.claim0.771