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

    Neuronpedia

    INDEX
    Explanations

    references to signatures in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    apollo
    -0.76
     feldspar
    -0.74
     Beal
    -0.69
     giudi
    -0.69
     Rudd
    -0.68
    AMIENTO
    -0.68
     Belinda
    -0.68
     Nix
    -0.67
    pulos
    -0.66
    boks
    -0.66
    POSITIVE LOGITS
     signatures
    1.54
     Signatures
    1.53
    Signatures
    1.43
     signature
    1.29
    signatures
    1.27
     Signature
    1.25
    Signature
    1.16
    signature
    1.10
    SIGNATURE
    1.09
     SIGNATURE
    1.03
    Act Density 0.003%

    No Known Activations