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

    Neuronpedia

    INDEX
    Explanations

    references to movies or film-related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of films and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    attled
    -0.69
    cffff
    -0.68
    itability
    -0.67
    rian
    -0.66
    lein
    -0.66
    iang
    -0.64
    ilities
    -0.64
    ciating
    -0.64
    bley
    -0.63
    bos
    -0.61
    POSITIVE LOGITS
    ography
    1.01
     adaptation
    1.00
    goers
    1.00
     studio
    0.99
     studios
    0.98
    ographies
    0.97
     premie
    0.94
    strip
    0.92
    film
    0.91
     productions
    0.88
    Act Density 0.078%

    No Known Activations