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

    Neuronpedia

    INDEX
    Explanations

    references to movies or the film industry

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "film" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffff
    -0.77
    BY
    -0.65
    esse
    -0.65
    bley
    -0.65
    itability
    -0.63
    rian
    -0.63
    abies
    -0.63
    ojure
    -0.63
    ilities
    -0.63
    ensional
    -0.62
    POSITIVE LOGITS
    film
    0.99
    Film
    0.98
    ography
    0.91
    ographies
    0.88
     adaptation
    0.87
     studios
    0.86
    ctors
    0.85
     films
    0.85
    goers
    0.84
    strip
    0.84
    Act Density 0.045%

    No Known Activations