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

    Neuronpedia

    INDEX
    Explanations

    descriptions or mentions of specific scenes within a narrative or visual medium

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    dp
    -1.17
    gemony
    -1.11
    iott
    -1.06
    berman
    -1.05
    secut
    -1.04
    thood
    -1.04
     Seym
    -1.03
    achev
    -1.01
    atever
    -1.00
    ternity
    -1.00
    POSITIVE LOGITS
    Dialogue
    1.26
     Scenes
    1.06
     Scene
    1.05
     scenes
    1.02
     involving
    1.02
    Capture
    1.00
    icles
    0.97
    LINE
    0.97
    scene
    0.94
     Supervisor
    0.90
    Act Density 2.028%

    No Known Activations