Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    evidence of claims, suggestions, or indicators in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SharedCtor
    -0.54
     Stays
    -0.53
    neous
    -0.52
    expandindo
    -0.52
     eats
    -0.52
     tors
    -0.52
    Faces
    -0.51
    abit
    -0.50
     GLFW
    -0.49
     ModelRenderer
    -0.49
    POSITIVE LOGITS
     suggests
    1.77
     indicates
    1.66
    indicates
    1.37
     implies
    1.36
     explains
    1.35
     sugiere
    1.21
     confirms
    1.20
     Indicates
    1.17
     demonstrates
    1.13
     illustrates
    1.13
    Act Density 0.236%

    No Known Activations