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

    Neuronpedia

    INDEX
    Explanations

    movie-related content such as movie titles, locations, and genres

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utive
    -0.69
    umen
    -0.67
    reth
    -0.62
    atively
    -0.62
    uto
    -0.61
    UF
    -0.60
    jured
    -0.59
    ¬¼
    -0.58
    ason
    -0.57
    iple
    -0.57
    POSITIVE LOGITS
     lest
    1.02
     albeit
    0.94
     wherein
    0.94
     aka
    0.92
     huh
    0.91
     namely
    0.88
     haha
    0.87
     eh
    0.86
     which
    0.85
     circa
    0.83
    Act Density 0.719%

    No Known Activations