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

    Neuronpedia

    INDEX
    Explanations

    names followed by a phrase thanking or acknowledging someone

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     largeDownload
    -0.68
    ãĤ¼ãĤ¦ãĤ¹
    -0.67
    isSpecialOrderable
    -0.60
    soDeliveryDate
    -0.58
    Introduced
    -0.56
    enabled
    -0.54
    Ranked
    -0.54
    ãĥĪ
    -0.53
    ĨĴ
    -0.51
    quickShipAvailable
    -0.51
    POSITIVE LOGITS
     for
    1.36
    for
    1.18
     FOR
    0.90
    For
    0.85
     For
    0.83
    FOR
    0.82
    ortium
    0.65
    é¾į
    0.62
    enburg
    0.61
     because
    0.61
    Act Density 0.556%

    No Known Activations