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

    Neuronpedia

    INDEX
    Explanations

    references to specific foreign names and locations

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols in the text, particularly those resembling letters with diacritics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DonaldTrump
    -0.72
    bread
    -0.69
    idious
    -0.67
    itious
    -0.67
     bearer
    -0.65
     crush
    -0.65
    utterstock
    -0.65
    icity
    -0.65
    iple
    -0.65
    enegger
    -0.64
    POSITIVE LOGITS
    ø
    1.06
    0.95
    ĺ
    0.95
    ħ
    0.89
    ¸
    0.89
    ¬
    0.87
    Å¡
    0.86
    hett
    0.86
    ĨĴ
    0.86
    rn
    0.86
    Act Density 0.007%

    No Known Activations