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

    Neuronpedia

    INDEX
    Explanations

    references to characters and plot points from various movies, TV shows, and literature

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     maxim
    -0.90
    ofi
    -0.88
    lihood
    -0.86
    jri
    -0.84
    abl
    -0.83
    DEN
    -0.83
    jab
    -0.81
    chwitz
    -0.81
     hunger
    -0.81
    bury
    -0.81
    POSITIVE LOGITS
    pmwiki
    1.04
    Characters
    0.98
    ãģĭ
    0.96
     Scenes
    0.91
     Kira
    0.89
     Nemesis
    0.87
     Gladiator
    0.86
     Scene
    0.85
    Altern
    0.85
     Episode
    0.84
    Act Density 0.279%

    No Known Activations