interpretability
alignment
constitutional AI
transformer-failure-analysis
refusal-diagnostic
advanced
transformer
models
recursion
refusal
hallucination
neural
attribution
sparse
autoencoder
superposition
Claude
DeepSeek
Gemini
ChatGPT
Grok
Mistral
Rosetta
Stone
pareto-lang
symbolic-residue
symbolic
residue
Update README.md
#1 opened 9 days ago
by
recursiveauto