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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with counts or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ویکی‌پدیای
    -1.05
     autorytatywna
    -0.99
     Мексичка
    -0.91
     ویکی‌پدی
    -0.89
    AndEndTag
    -0.88
    httphttps
    -0.85
     समीक्षक
    -0.85
     MotionEvent
    -0.84
    AutoresizingMask
    -0.83
    المشاركات
    -0.82
    POSITIVE LOGITS
    lees
    0.60
    0
    0.53
    less
    0.51
     diễn
    0.49
     Caes
    0.48
     skrzy
    0.47
    ைய
    0.47
    my
    0.46
    ぐれ
    0.46
    ۰۰
    0.46
    Act Density 0.359%

    No Known Activations