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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific character sequences or formatting indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.87
    ⓧ
    -0.64
    hisattva
    -0.58
    ("$.
    -0.57
    حياتها
    -0.57
     Firms
    -0.57
    حياته
    -0.57
    evos
    -0.57
     باخ
    -0.56
    SourceChecksum
    -0.56
    POSITIVE LOGITS
    <bos>
    0.82
    Xna
    0.58
    ędzynarod
    0.58
     ElementRef
    0.54
    AlterField
    0.53
     Saltar
    0.51
    Hochspringen
    0.49
    NUMX
    0.47
    ModelSerializer
    0.47
    ’
    0.45
    Act Density 0.122%

    No Known Activations