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

    Neuronpedia

    INDEX
    Explanations

    references to animated series and content creators in the entertainment industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.16
    3:0.14
    4:0.23
    5:0.02
    6:0.02
    7:0.08
    8:0.04
    9:0.04
    10:0.09
    11:0.08
    Negative Logits
    ieu
    -1.79
    UTC
    -1.75
    lished
    -1.70
    ustomed
    -1.65
     onlook
    -1.65
     muted
    -1.61
    Magikarp
    -1.61
    oyer
    -1.54
     tremend
    -1.53
    isher
    -1.52
    POSITIVE LOGITS
    thood
    1.93
     Cups
    1.58
     portfolio
    1.50
     titles
    1.50
     virginity
    1.46
     portfolios
    1.46
     Nicotine
    1.45
     breakout
    1.45
     Proposition
    1.44
     assignments
    1.44
    Act Density 0.130%

    No Known Activations