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

    Neuronpedia

    INDEX
    Explanations

    titles of episodes from a specific TV show

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     spons
    -0.84
    ucl
    -0.79
     benches
    -0.76
    staking
    -0.71
    buck
    -0.71
    usra
    -0.69
    unicip
    -0.68
    lav
    -0.68
    elong
    -0.67
     occas
    -0.65
    POSITIVE LOGITS
     Chronicles
    1.22
     sequel
    1.14
     Ultimate
    1.06
     Apocalypse
    1.04
     Deluxe
    1.02
     Generations
    0.97
     Dracula
    0.96
     Grimoire
    0.96
     Wii
    0.95
     Rivals
    0.94
    Act Density 0.154%

    No Known Activations