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

    Neuronpedia

    INDEX
    Explanations

    trailer-related content and references to popular culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.28
    1:0.02
    2:0.09
    3:0.10
    4:0.04
    5:0.07
    6:0.08
    7:0.04
    8:0.06
    9:0.09
    10:0.06
    11:0.01
    Negative Logits
     Faust
    -2.57
     Schwar
    -2.55
    Sax
    -2.50
     Berkshire
    -2.45
     Exchange
    -2.45
     mathemat
    -2.43
     Phi
    -2.43
    metics
    -2.41
    odox
    -2.36
     quartz
    -2.35
    POSITIVE LOGITS
     trailer
    7.41
     trailers
    6.99
     Trailer
    6.21
     teaser
    5.37
     spoiler
    4.38
     spoilers
    4.08
     previews
    3.94
     footage
    3.87
     cinematic
    3.71
    Spoiler
    3.69
    Act Density 0.026%

    No Known Activations