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

    Neuronpedia

    INDEX
    Explanations

    French language terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "de" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyomi
    -0.89
     Flavoring
    -0.87
    DragonMagazine
    -0.82
     Wage
    -0.78
    ĸļ
    -0.77
    ocene
    -0.75
    ãĤ¤ãĥĪ
    -0.72
     AAP
    -0.72
    ORY
    -0.71
     Kingdoms
    -0.70
    POSITIVE LOGITS
    cember
    1.01
     jour
    0.99
     Blasio
    0.97
    arest
    0.96
    activate
    0.94
    uce
    0.91
    uces
    0.91
     facto
    0.89
    legate
    0.89
     la
    0.88
    Act Density 0.016%

    No Known Activations