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

    Neuronpedia

    INDEX
    Explanations

    Chinese characters and numerals

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -1.00
    puter
    -0.99
    ufact
    -0.96
    nesota
    -0.86
     adolesc
    -0.83
    ittee
    -0.79
    awaru
    -0.79
    byter
    -0.78
     satell
    -0.78
    wcs
    -0.77
    POSITIVE LOGITS
    ³
    1.13
    ت
    1.05
    ´
    1.01
    ÙĨ
    1.00
    ł
    0.99
    Ùħ
    0.90
    ï¸ı
    0.84
    л
    0.82
    µ
    0.82
    ÙĬ
    0.82
    Act Density 0.003%

    No Known Activations