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

    Neuronpedia

    INDEX
    Explanations

    French words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of non-English words or foreign language elements in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adden
    -0.80
    helps
    -0.66
    aunder
    -0.65
    uese
    -0.64
     Genesis
    -0.64
     Ritual
    -0.64
    ographs
    -0.63
    ousy
    -0.62
    iazep
    -0.62
    ously
    -0.61
    POSITIVE LOGITS
    ré
    0.94
    izoph
    0.93
     Qué
    0.88
    bec
    0.87
    sth
    0.82
     pse
    0.80
    dain
    0.76
     é
    0.74
    enne
    0.74
    nai
    0.74
    Act Density 0.013%

    No Known Activations