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

    Neuronpedia

    INDEX
    Explanations

    references to specific visual scenes or sequences in movies

    oai_token-act-pair · gpt-3.5-turbo

    references to specific scenes in movies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achev
    -0.92
    uyomi
    -0.83
    icrobial
    -0.80
    sonian
    -0.74
    izo
    -0.74
    rition
    -0.72
    dp
    -0.72
    orem
    -0.72
    gently
    -0.72
    acid
    -0.71
    POSITIVE LOGITS
    Dialogue
    0.98
     Scenes
    0.98
     scenes
    0.95
     involving
    0.92
    scene
    0.90
     Scene
    0.87
     depicting
    0.79
     VIDE
    0.77
     Supervisor
    0.77
    acters
    0.75
    Act Density 0.024%

    No Known Activations