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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically commas, in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uma
    -0.16
    loat
    -0.15
    âce
    -0.15
    jez
    -0.14
    ute
    -0.14
    foy
    -0.14
    ÄĻ
    -0.14
    æĸ
    -0.14
    zej
    -0.14
    UTE
    -0.14
    POSITIVE LOGITS
    arges
    0.16
    errat
    0.15
    unik
    0.15
     DISCLAIM
    0.15
     com
    0.15
    lernen
    0.14
    794
    0.14
    ensem
    0.14
    Nr
    0.14
    ÑĢоÑĩ
    0.14
    Act Density 0.046%

    No Known Activations