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

    Neuronpedia

    INDEX
    Explanations

    movies or film-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to films and movies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    姫
    -0.82
    maxwell
    -0.74
    MpServer
    -0.73
    aples
    -0.70
    ido
    -0.70
     Individuals
    -0.67
    hidden
    -0.67
    oqu
    -0.66
    UTC
    -0.65
    Nature
    -0.64
    POSITIVE LOGITS
     starring
    1.29
     adaptation
    1.28
     sequel
    1.20
     trilogy
    1.09
     sequels
    1.08
     screenplay
    1.06
     premiered
    1.01
     slated
    1.01
     Paramount
    1.00
     franchise
    0.98
    Act Density 0.224%

    No Known Activations