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

    Neuronpedia

    INDEX
    Explanations

    French words with accents

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "é" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utterstock
    -0.79
    pread
    -0.78
    enged
    -0.74
     redistributed
    -0.70
    Downloadha
    -0.69
    uyomi
    -0.69
    ageddon
    -0.67
    Spread
    -0.66
    multipl
    -0.66
     Lovecraft
    -0.66
    POSITIVE LOGITS
    lé
    1.21
     Dame
    0.96
    é
    0.96
     é
    0.93
    és
    0.90
    cé
    0.88
    ité
    0.87
    rique
    0.86
    rez
    0.84
    vez
    0.82
    Act Density 0.009%

    No Known Activations