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

    Neuronpedia

    INDEX
    Explanations

    references to "signatures" or "signature" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anyeol
    -0.73
    ers
    -0.70
     ExecuteAsync
    -0.66
     kezd
    -0.65
    samt
    -0.65
    arkov
    -0.65
     couteau
    -0.63
    ellingham
    -0.61
     Auk
    -0.61
     Rudd
    -0.60
    POSITIVE LOGITS
     signatures
    1.77
     signature
    1.75
     Signatures
    1.71
     Signature
    1.67
    Signatures
    1.53
    Signature
    1.52
    signature
    1.51
     SIGNATURE
    1.35
    signatures
    1.34
    SIGNATURE
    1.20
    Act Density 0.109%

    No Known Activations