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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating quantity or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.79
    Portale
    -0.78
     للمعارف
    -0.76
     بيها
    -0.72
     فريبيس
    -0.68
     InputDecoration
    -0.68
     EconPapers
    -0.63
    出版年
    -0.61
     '\\;'
    -0.61
     isNameExpr
    -0.61
    POSITIVE LOGITS
     five
    0.95
     six
    0.94
     four
    0.94
     three
    0.93
     two
    0.85
     eight
    0.83
     seven
    0.82
     nine
    0.73
     ten
    0.68
     cinco
    0.68
    Act Density 0.332%

    No Known Activations