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

    Neuronpedia

    INDEX
    Explanations

    French words and accents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     redistributed
    -0.77
    etsk
    -0.77
    pread
    -0.69
    utterstock
    -0.69
    enged
    -0.66
    ageddon
    -0.65
     hover
    -0.64
     Cobra
    -0.64
    INESS
    -0.62
    Spread
    -0.61
    POSITIVE LOGITS
    lé
    1.10
    rique
    0.94
    vez
    0.93
    mie
    0.92
    ration
    0.92
    ré
    0.86
     Dame
    0.86
    rez
    0.86
    rie
    0.86
    cé
    0.84
    Act Density 0.018%

    No Known Activations