concept
active
concept:strict-output-surjectivity

Strict Output-Surjectivity

Assumption that every output class can be produced by the DNN in each layer; key condition for Theorem 1

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • Failure mode for output-surjectivity: LLMs may lack capacity to predict all tokens due to rank constraints

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.

  • Output-truthconcept0.742
    The correctness of a model's generated outputs, distinct from the correctness of statements provided as input.
  • Mechanistic finding by Bricken et al. 2023 about how LLMs store features; cited as operational justification for pattern-repository assumption
  • Foundational claim derived from the Free Energy Principle, setting up self-evidencing.
  • 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.
  • The core imperative under the Free Energy Principle; systems must reduce the difference between predicted and actual sensory states.
  • Specification relating a program's inputs and outputs, analogous to illocutionary correctness.
  • Diagrammatic encoding of program behavior via concept lattices reveals reachability structure and non-determinism without fixed calculational rules.
  • Output Diversityconcept0.703
    The breadth of distinct outputs an LLM can produce, which is reduced by mode collapse after alignment training