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

    Neuronpedia

    INDEX
    Explanations

    references to horror or action movies, particularly with violent or intense themes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    uration
    -0.67
    xual
    -0.62
    fty
    -0.62
    unity
    -0.61
    antly
    -0.60
    ciation
    -0.59
    efully
    -0.59
    eering
    -0.58
    ĸļ
    -0.58
    ERC
    -0.57
    POSITIVE LOGITS
    spin
    0.82
     Redemption
    0.77
    liest
    0.71
    pool
    0.70
    ritten
    0.68
    riter
    0.67
    rick
    0.67
     Alive
    0.67
    lift
    0.66
    soever
    0.65
    Act Density 6.986%

    No Known Activations