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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific terms related to art, film, and literature

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    âĹ¼
    -0.87
     Boone
    -0.71
    upt
    -0.69
    ask
    -0.67
    realDonaldTrump
    -0.66
    oke
    -0.65
     Clever
    -0.65
     mater
    -0.65
    hip
    -0.63
    ç¥ŀ
    -0.60
    POSITIVE LOGITS
     Fighters
    0.93
    ruary
    0.91
    letcher
    0.91
    ruits
    0.89
    luent
    0.85
    ornia
    0.83
    andom
    0.81
    ocused
    0.80
    ergus
    0.80
    iture
    0.79
    Act Density 11.079%

    No Known Activations