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

    Neuronpedia

    INDEX
    Explanations

    mentions of the Quran

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.06
    2:0.07
    3:0.09
    4:0.09
    5:0.08
    6:0.09
    7:0.09
    8:0.08
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
     Indigenous
    -3.08
     Aboriginal
    -2.93
     Ak
    -2.60
    �
    -2.56
     Haf
    -2.53
     Rohingya
    -2.52
    ga
    -2.52
     unsu
    -2.44
     Ig
    -2.43
     Shield
    -2.43
    POSITIVE LOGITS
    phabet
    3.64
     scen
    3.09
     quar
    2.71
     embr
    2.64
     thous
    2.60
     livest
    2.53
    rawdownloadcloneembedreportprint
    2.45
     recess
    2.45
    ◼
    2.45
    puter
    2.43
    Act Density 0.000%

    No Known Activations