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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ongoing actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [*]
    -0.52
    மான
    -0.50
    oden
    -0.47
    tra
    -0.47
    dar
    -0.46
     derecho
    -0.46
    福利
    -0.45
    anger
    -0.45
    gub
    -0.45
    wsze
    -0.44
    POSITIVE LOGITS
     estekak
    0.82
    LookAnd
    0.79
     Wikimedijinoj
    0.71
    Hauptartikel
    0.70
     propOrder
    0.69
     pescoço
    0.67
    ItemBackground
    0.67
    WireFormatLite
    0.67
    complexContent
    0.65
    setVerticalGroup
    0.65
    Act Density 0.545%

    No Known Activations