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

    Neuronpedia

    INDEX
    Explanations

    numeric data and specific formatting in technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ught
    -0.17
    ajor
    -0.15
    gard
    -0.14
    ountains
    -0.14
    erv
    -0.14
    анÑģов
    -0.14
    é
    -0.14
    ought
    -0.13
    vor
    -0.13
    QA
    -0.13
    POSITIVE LOGITS
    (s
    0.21
    zv
    0.16
    ä¸įçŁ¥
    0.15
    coes
    0.15
    sembl
    0.15
    ekim
    0.15
    [s
    0.14
    elpers
    0.14
    ENA
    0.14
    ozo
    0.14
    Act Density 0.775%

    No Known Activations