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

    Neuronpedia

    INDEX
    Explanations

    numerical values or numeric expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.70
     autorytatywna
    -0.70
    <bos>
    -0.66
    CloseOperation
    -0.62
    تقاوى
    -0.60
    存于互联网档案馆
    -0.59
     eşofman
    -0.57
    ikusbot
    -0.57
    orianCalendar
    -0.56
    avelength
    -0.56
    POSITIVE LOGITS
    2
    1.41
    3
    0.66
    ２
    0.63
    4
    0.60
    deux
    0.52
    ২
    0.50
    ۲
    0.50
    two
    0.50
     TWO
    0.49
     ২
    0.49
    Act Density 1.058%

    No Known Activations