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

    Neuronpedia

    INDEX
    Explanations

    Welcome messages

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itud
    -0.71
    Ga
    -0.69
     Dayton
    -0.68
    azz
    -0.67
    ikk
    -0.66
     wip
    -0.66
    bilt
    -0.63
     coc
    -0.62
     Constantin
    -0.62
    cko
    -0.61
    POSITIVE LOGITS
     actionGroup
    0.72
    ategory
    0.71
    yrics
    0.68
    SHARE
    0.65
    Enabled
    0.63
     Utilities
    0.62
    udeb
    0.61
    deen
    0.61
    OTS
    0.60
    ļéĨĴ
    0.60
    Act Density 0.000%

    No Known Activations