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

    Neuronpedia

    INDEX
    Explanations

    movie titles

    oai_token-act-pair · gpt-3.5-turbo

    titles of films and shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     waivers
    -0.73
    terday
    -0.69
     capacities
    -0.69
     deleg
    -0.68
     eligible
    -0.67
     stringent
    -0.66
    itionally
    -0.66
    TN
    -0.66
     reservations
    -0.65
     sensit
    -0.64
    POSITIVE LOGITS
     Trilogy
    1.14
     Awakens
    1.07
     Angels
    1.01
     Reborn
    0.95
     Boys
    0.93
     Swordsman
    0.91
     soundtrack
    0.90
     Bride
    0.87
     Thing
    0.87
     Brigade
    0.87
    Act Density 0.250%

    No Known Activations