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

    references to famous movies and their titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itably
    -0.94
    theless
    -0.89
    tem
    -0.86
    itable
    -0.82
    perm
    -0.80
    bish
    -0.79
    iliated
    -0.78
    estern
    -0.74
    sche
    -0.73
    ospons
    -0.73
    POSITIVE LOGITS
     Assassin
    1.09
     Predator
    1.02
     Assassins
    0.97
     Peaks
    0.95
     Trilogy
    0.93
     Armor
    0.90
     Drone
    0.86
     Creed
    0.86
     Protocol
    0.86
     Reaper
    0.84
    Act Density 0.026%

    No Known Activations