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

    Neuronpedia

    INDEX
    Explanations

    narrative scenes involving characters and their actions in a TV show or movie

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    brand
    -0.81
    ikes
    -0.80
    bred
    -0.76
     consortium
    -0.75
    soType
    -0.72
    ifestyle
    -0.72
    iership
    -0.71
    raft
    -0.70
    branded
    -0.70
     decentralized
    -0.69
    POSITIVE LOGITS
     narration
    1.18
     flashback
    1.00
     climax
    0.98
    Characters
    0.98
     Scenes
    0.97
     scenes
    0.97
     narrator
    0.94
    scene
    0.94
     cinematic
    0.94
     narr
    0.94
    Act Density 0.499%

    No Known Activations