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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases that introduce or refer to new topics or sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    셨
    -0.67
    ってみる
    -0.67
    てもら
    -0.65
    <bos>
    -0.63
     सकती
    -0.61
    ればいい
    -0.60
    ceğine
    -0.57
    getSingle
    -0.57
    ってみました
    -0.56
    нулись
    -0.55
    POSITIVE LOGITS
    parsedMessage
    0.93
    UnsafeEnabled
    0.91
    Personensuche
    0.90
    setVerticalGroup
    0.89
    DockStyle
    0.88
    GEBURTSDATUM
    0.83
    LookAnd
    0.81
     Normdatei
    0.78
    StructEnd
    0.77
     Roskov
    0.76
    Act Density 20.553%

    No Known Activations