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

    Neuronpedia

    INDEX
    Explanations

    technical terms and expressions related to mathematical concepts and computational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Senti
    -0.48
     Cho
    -0.46
    dia
    -0.45
    ASS
    -0.45
     <<<
    -0.45
     Cid
    -0.45
    gom
    -0.43
     Tik
    -0.43
    rass
    -0.42
    getC
    -0.42
    POSITIVE LOGITS
    uxxxx
    0.92
     nakalista
    0.77
     okuyayım
    0.72
    الإنجليزية
    0.72
     ویکی‌پدیا
    0.70
    पया
    0.68
    UnsafeEnabled
    0.67
    ftagPool
    0.67
    TargetException
    0.67
     auguri
    0.67
    Act Density 0.494%

    No Known Activations