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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating extremes or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Unione
    -0.47
    ად
    -0.47
     doença
    -0.46
     genoux
    -0.45
    net
    -0.45
    nter
    -0.44
    LOAD
    -0.43
    site
    -0.43
    ボ
    -0.43
    <
    -0.43
    POSITIVE LOGITS
    SharedDtor
    0.78
     الحره
    0.77
    offsetof
    0.75
     AssemblyCompany
    0.73
     itſelf
    0.72
    исленность
    0.72
     contextLoads
    0.71
     greateſt
    0.71
    NUMX
    0.70
     nhat
    0.69
    Act Density 0.126%

    No Known Activations