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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions related to probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (\<
    -0.50
     defaultstate
    -0.50
    endcsname
    -0.49
     ویکی‌پدی
    -0.49
    devamını
    -0.49
    ronpa
    -0.48
    ropriate
    -0.48
    citroën
    -0.47
     autorytatywna
    -0.46
    UnsafeEnabled
    -0.46
    POSITIVE LOGITS
    новништво
    0.39
     Wordle
    0.35
    Tm
    0.31
     hozzá
    0.31
    LEADING
    0.31
     acom
    0.30
     sitten
    0.30
    0.30
    exitRule
    0.30
    NewUrlParser
    0.30
    Act Density 0.790%

    No Known Activations