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

    Neuronpedia

    INDEX
    Explanations

    dates and chronological events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dorp
    -0.52
    usehen
    -0.52
    intégr
    -0.51
     ioutil
    -0.50
    sprüng
    -0.50
     the
    -0.50
     banyak
    -0.50
     tr
    -0.49
     H
    -0.49
    heits
    -0.48
    POSITIVE LOGITS
     Himo
    0.81
     itſelf
    0.79
    WireFormatLite
    0.77
    KommentareTeilen
    0.75
    ArrowToggle
    0.73
    מבר
    0.70
     betweenstory
    0.68
     auffi
    0.65
    PreferredItem
    0.64
     ―――――
    0.63
    Act Density 0.195%

    No Known Activations