The paper does not claim that the LLM itself is the source of meaning and value, only that meaning can be discerned in its output.

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

• We hypothesize that LLMs represent correctness of arithmetic expressions differently from factual statements.hypothesis0.808
  Core working hypothesis motivating the factual vs. arithmetic task split in the experimental design.
• LLMs linearly represent truth-relevant information beyond the plausibility of text, as evidenced by probes trained on likely performing poorly on anti-correlated datasetsclaim0.798
  Establishes that the observed linear structure is not merely a representation of text probability
• we believe the answer to the paper’s eponymous question is yes. Meaning and value can be ascribed to an AI-generated “sacred” text.quote0.796
  Authors' concluding statement of their central thesis.
• LLMs sometimes know statements are false but generate them anyway, motivating the need for techniques that inspect internal model state rather than outputs aloneclaim0.796
  Motivating claim supported by the CAPTCHA example and Perez et al. (2022) findings
• LLM self-reports about consciousness and moral significance should express degrees of confidence and provide context.claim0.789
  Recommendation for companies on LM outputs.
• When LLMs produce experience claims under self-reference, is this sophisticated simulation or genuine self-representation, and how would we tell the difference?question0.787
  The core interpretive question the paper narrows but cannot definitively answer
• LLMs can predict their own responses more accurately than external observers, implying privileged internal knowledgefinding0.785
  Binder et al. finding cited as evidence that LLMs possess introspective capacity analogous to mindfulness
• Automated interpretability using LLMs can usefully score feature specificity.claim0.785
  Claude 3 Opus ratings aligned with human judgment of feature descriptions.