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

    Neuronpedia

    INDEX
    Explanations

    the letter 'r'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.07
    3:0.09
    4:0.08
    5:0.08
    6:0.07
    7:0.07
    8:0.09
    9:0.08
    10:0.09
    11:0.07
    Negative Logits
    cule
    -2.94
    hattan
    -2.92
    tainment
    -2.83
    ocious
    -2.77
    uggle
    -2.76
    gew
    -2.71
     Gotham
    -2.70
     Lucius
    -2.63
    abiding
    -2.57
    ++;
    -2.56
    POSITIVE LOGITS
     CST
    2.90
     Nich
    2.78
     MN
    2.74
     Esk
    2.70
     Om
    2.68
     Dul
    2.67
     Indigenous
    2.63
     Nun
    2.59
     Aboriginal
    2.56
     NFC
    2.51
    Act Density 0.000%

    No Known Activations