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

    Neuronpedia

    INDEX
    Explanations

    names of actors and actresses, as well as movie titles

    oai_token-act-pair · gpt-3.5-turbo

    names of directors and cast members in film and television

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     deval
    -0.84
     futile
    -0.75
    osphere
    -0.75
    rencies
    -0.74
    ifact
    -0.73
     "$:/
    -0.72
    ctory
    -0.69
    til
    -0.69
    Unix
    -0.68
    osate
    -0.68
    POSITIVE LOGITS
     actor
    1.09
     cinem
    1.05
     actors
    1.02
     actress
    1.01
     actresses
    0.99
     Actress
    0.96
     Actor
    0.95
     Judd
    0.94
     Scenes
    0.93
     Baz
    0.93
    Act Density 0.325%

    No Known Activations