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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a range or variety of options or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (['/
    -0.14
    udging
    -0.14
    ReturnValue
    -0.14
     Conce
    -0.14
    ystone
    -0.14
    eln
    -0.14
    orners
    -0.14
    isel
    -0.14
    enco
    -0.13
     Skin
    -0.13
    POSITIVE LOGITS
    azo
    0.15
    alık
    0.14
    Bars
    0.14
     ÐĵÑĢи
    0.14
    ìĿ¸ìĿĺ
    0.14
    баÑģ
    0.14
    UpDown
    0.14
    dash
    0.14
    -ci
    0.14
    cola
    0.13
    Act Density 0.008%

    No Known Activations