concept
active
concept:self-identity-featuresSelf-identity features
Features that activate when the model is asked about itself, invoking AI tropes and anthropomorphization.
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.
- Extended identity and sense of self; in Mahāyāna Buddhism, perceived as permeable and co-constituted with others.
- The philosophical question of what constitutes identity over time, applied to the problem of what a dialogue agent would seek to preserve
- Structural and functional property exhibited by living systems but currently absent from most engineered machines.
- Open question from the discussion on future research directions.
- Process of reifying one's identity as an independent self; meditation practices aim to decrease selfing.
- Representations inside LLMs that can be intervened upon.
- Ability of a model to predict its own outputs or behavior, sometimes distinguished from introspection.