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

    Neuronpedia

    INDEX
    Explanations

    references to religious themes and censorship issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.23
    1:0.06
    2:0.04
    3:0.09
    4:0.08
    5:0.02
    6:0.10
    7:0.11
    8:0.03
    9:0.04
    10:0.09
    11:0.06
    Negative Logits
     Bowser
    -3.76
    ovych
    -3.57
     Snake
    -3.41
     Sounders
    -3.39
    Seattle
    -3.30
    Snake
    -3.23
     Mario
    -3.22
     streetcar
    -3.20
     Leafs
    -3.02
    Mario
    -2.99
    POSITIVE LOGITS
     blasphemy
    8.14
     blasp
    6.79
    hemy
    5.04
     clerics
    4.44
     lyn
    4.41
    Pakistan
    4.28
     Koran
    4.23
     Quran
    4.09
    Muslims
    4.06
     Prophet
    4.06
    Act Density 0.002%

    No Known Activations