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

    Neuronpedia

    INDEX
    Explanations

    elements related to public controversies and allegations, particularly those involving backlash and scrutiny

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.10
    3:0.41
    4:0.11
    5:0.02
    6:0.03
    7:0.07
    8:0.03
    9:0.04
    10:0.06
    11:0.06
    Negative Logits
    externalActionCode
    -1.91
     サーティワン
    -1.86
    ��
    -1.85
    thumbnails
    -1.79
     [+
    -1.74
    ��
    -1.73
    ��
    -1.72
                    
    -1.71
    EStreamFrame
    -1.71
    ��極
    -1.66
    POSITIVE LOGITS
     unorthodox
    1.88
    owered
    1.70
     cryptoc
    1.69
    htaking
    1.67
     outlandish
    1.65
     pricey
    1.64
     unconventional
    1.64
     frivol
    1.63
     cryptocurrencies
    1.62
     puzzling
    1.60
    Act Density 0.073%

    No Known Activations