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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to historical figures and geopolitical events, specifically focusing on names starting with "Fran" or variations thereof

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    scape
    -0.66
    footed
    -0.62
    ding
    -0.59
    ammed
    -0.59
    TPPStreamerBot
    -0.58
    holders
    -0.58
    accompanied
    -0.57
     stakes
    -0.55
    arov
    -0.55
    iqueness
    -0.55
    POSITIVE LOGITS
     Dres
    0.87
    furt
    0.83
    ois
    0.77
    izon
    0.68
     Kafka
    0.68
    Fran
    0.67
     Hollande
    0.67
     Vog
    0.65
    opol
    0.65
     Fran
    0.64
    Act Density 9.007%

    No Known Activations