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

    Neuronpedia

    INDEX
    Explanations

    names of movies and actors

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     podium
    -0.81
     PSU
    -0.77
     benches
    -0.76
     exch
    -0.75
     moderation
    -0.70
    ItemTracker
    -0.68
     porous
    -0.68
     fiat
    -0.68
     knowledgeable
    -0.67
    hops
    -0.67
    POSITIVE LOGITS
     Chronicles
    1.07
     Trilogy
    0.99
     sequels
    0.97
     trilogy
    0.96
     starring
    0.95
     Girl
    0.95
     Adventures
    0.94
     Deadly
    0.94
     Vampire
    0.94
     Martian
    0.93
    Act Density 0.328%

    No Known Activations