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

    Neuronpedia

    INDEX
    Explanations

    tokens related to mathematical concepts and numerical values

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Efq
    -0.70
     GenerationType
    -0.68
    脚注の使い方
    -0.68
     thither
    -0.65
     himſelf
    -0.64
    WriteBarrier
    -0.62
     ContentValues
    -0.61
    ſelves
    -0.61
     purpoſe
    -0.61
     itſelf
    -0.61
    POSITIVE LOGITS
    amon
    0.61
     str
    0.54
    //:
    0.50
    str
    0.50
    WithIOException
    0.48
    QS
    0.47
    hame
    0.47
     Martin
    0.47
    Wal
    0.47
    ingo
    0.46
    Act Density 0.022%

    No Known Activations