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

    Neuronpedia

    INDEX
    Explanations

    numerical values or references to mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ویکی‌پدیای
    -0.77
    ———-
    -0.76
    WART
    -0.72
    })).
    -0.70
     έν
    -0.69
     }}"></
    -0.66
     متعلقه
    -0.65
    }`).
    -0.65
     Rahman
    -0.63
    kuuta
    -0.63
    POSITIVE LOGITS
    5
    2.31
     Five
    1.31
    ۵
    1.29
    ５
    1.28
    ⁵
    1.24
    6
    1.21
    ५
    1.20
     Fifth
    1.19
    4
    1.19
     FIVE
    1.19
    Act Density 0.794%

    No Known Activations