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

    Neuronpedia

    INDEX
    Explanations

    accents and characters from non-English languages

    oai_token-act-pair · gpt-3.5-turbo

    special characters and accented letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayson
    -0.70
    urg
    -0.68
    ORE
    -0.66
    alez
    -0.65
    IFIED
    -0.65
    ifiers
    -0.63
    ulse
    -0.63
    dfx
    -0.62
    ifier
    -0.62
    OWER
    -0.60
    POSITIVE LOGITS
     la
    1.04
    ï
    0.85
    gypt
    0.82
    ´
    0.77
    VERTISEMENT
    0.76
    ¯¯¯¯
    0.74
    ¯
    0.73
    ħĭ
    0.73
     jour
    0.72
     tro
    0.72
    Act Density 0.013%

    No Known Activations