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

    Neuronpedia

    INDEX
    Explanations

    non-English characters or symbols within the text

    oai_token-act-pair · gpt-3.5-turbo

    the presence of special characters or formatting markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.79
     Crom
    -0.77
    thood
    -0.74
    urden
    -0.73
    $$
    -0.70
    oba
    -0.69
    ovan
    -0.69
    ebted
    -0.69
    mable
    -0.66
    ahime
    -0.65
    POSITIVE LOGITS
    Ŀ
    1.07
    ³
    1.05
    ±
    1.05
    ¦
    1.04
    ¡
    0.98
    ¹
    0.97
    0.95
    ª
    0.94
    ł
    0.92
    ·
    0.90
    Act Density 0.063%

    No Known Activations