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

    Neuronpedia

    INDEX
    Explanations

    references to scenes in narratives or performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.07
    3:0.09
    4:0.05
    5:0.03
    6:0.03
    7:0.10
    8:0.03
    9:0.05
    10:0.34
    11:0.12
    Negative Logits
     treasurer
    -1.61
     certification
    -1.56
     certified
    -1.52
     cryptocurrencies
    -1.46
    legal
    -1.41
     certify
    -1.40
    folio
    -1.39
     financially
    -1.38
    Health
    -1.38
     founder
    -1.38
    POSITIVE LOGITS
     cinematic
    2.04
     Kubrick
    1.93
     sequence
    1.91
     cinem
    1.81
     narration
    1.80
    Narr
    1.75
     flashback
    1.73
     Scene
    1.72
    Characters
    1.70
    Scene
    1.67
    Act Density 0.061%

    No Known Activations