logical representation of programs

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

• Linear representationconcept0.808
  The idea that features are encoded as directions in activation space.
• concept representationconcept0.784
  How a neural network encodes a semantic concept internally, argued to be better captured by manifolds than by atomic features.
• No special theory of programming is required to prove properties of programs if they are expressed as logical sentences.claim0.784
  Key claim of the Algol 48/50 and Elephant approach.
• Linear Representation of Featuresconcept0.770
  The central object of study — the idea that a concept like truth is encoded as a direction in the LLM's latent space
• Linear Representation of Concepts in LLMsconcept0.770
  The finding that interpretable concepts including character traits are encoded as linear directions in transformer residual streams
• shared logical variablesconcept0.763
  Uninstantiated variables used for communication in concurrent logic programming.
• Structure in representationsconcept0.760
  The central question of whether representational geometry implies corresponding computational structure
• A computer program is not defined by its language or hardware but as an abstract causal pattern, a dynamic mathematical structure that influences the physical universe without violating its causal closure.claim0.757
  Paper's ontological characterization of software enabling cyberanimism