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

    Neuronpedia

    INDEX
    Explanations

    references to the Quran

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.09
    2:0.08
    3:0.07
    4:0.09
    5:0.08
    6:0.07
    7:0.07
    8:0.09
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
    ouver
    -3.66
    ustom
    -3.24
    llan
    -3.03
    avour
    -2.94
     onwards
    -2.86
    hao
    -2.82
    ophon
    -2.81
    ‐
    -2.77
    anging
    -2.74
    oad
    -2.69
    POSITIVE LOGITS
     Sears
    3.87
     Presbyterian
    3.81
     Episcopal
    3.80
     BART
    3.79
     Judaism
    3.78
     Amtrak
    3.52
     Schne
    3.51
     Rutgers
    3.50
     synagogue
    3.47
     Bridgewater
    3.34
    Act Density 0.000%

    No Known Activations