OS-Software/llm-jp-4.1-33b-thinking-uncensored-heretic
Abliterated vs llm-jp/llm-jp-4.1-33b-thinking. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 10 of 64 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 10/192, Attention 10/256, lm_head 0/1