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

    Neuronpedia

    INDEX
    Explanations

    references to movies

    oai_token-act-pair · gpt-3.5-turbo

    references to movies or cinematic elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raham
    -0.72
    existent
    -0.71
    cffff
    -0.69
    ²¾
    -0.68
     broken
    -0.67
    bleacher
    -0.66
    ĵĺ
    -0.65
    uckles
    -0.65
    minded
    -0.63
    omaly
    -0.62
    POSITIVE LOGITS
     theater
    1.08
     theaters
    1.07
    goers
    1.02
     movie
    0.99
     theatre
    0.99
     movies
    0.95
     theat
    0.90
    movie
    0.88
    Movie
    0.86
    arium
    0.85
    Act Density 0.038%

    No Known Activations