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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to programming or coding tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UIControlState
    -0.56
    windowFixed
    -0.53
    Prefs
    -0.50
    uegos
    -0.49
     &___
    -0.49
     noexcept
    -0.49
     recommandée
    -0.48
     وتسجيلات
    -0.48
    ropolis
    -0.48
    goku
    -0.48
    POSITIVE LOGITS
     filler
    0.78
     tartalomajánló
    0.69
     Walkover
    0.68
    filler
    0.66
    Filler
    0.64
    <bos>
    0.64
     gap
    0.63
     otherwise
    0.61
    otherwise
    0.61
     Filler
    0.60
    Act Density 0.572%

    No Known Activations