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

    Neuronpedia

    INDEX
    Explanations

    statements about civic or political disenfranchisement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.04
    2:0.07
    3:0.07
    4:0.03
    5:0.05
    6:0.22
    7:0.04
    8:0.09
    9:0.21
    10:0.02
    11:0.03
    Negative Logits
     Shard
    -4.57
     oy
    -4.51
     NYU
    -3.96
     Ox
    -3.75
     Hou
    -3.69
     Nem
    -3.61
     Katz
    -3.57
     Podesta
    -3.56
    SEA
    -3.46
    ITE
    -3.41
    POSITIVE LOGITS
     Calvin
    10.77
    Cal
    4.82
    avis
    4.80
    vin
    4.78
     Luther
    4.61
     Alvin
    4.32
     Crus
    4.30
     sin
    4.16
     Marvin
    4.05
    sin
    4.01
    Act Density 0.000%

    No Known Activations