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

    Neuronpedia

    INDEX
    Explanations

    statements about social justice issues and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.02
    2:0.06
    3:0.04
    4:0.05
    5:0.03
    6:0.22
    7:0.06
    8:0.07
    9:0.28
    10:0.02
    11:0.04
    Negative Logits
    Hom
    -4.17
     fec
    -3.70
    ubs
    -3.69
    FE
    -3.68
     tub
    -3.58
    hom
    -3.54
     suc
    -3.50
    ンジ
    -3.48
    FB
    -3.42
     Woo
    -3.40
    POSITIVE LOGITS
     Alexander
    9.90
    Alexander
    9.45
     ALE
    5.67
     Alexandra
    4.54
     Allen
    4.39
     Atkinson
    4.28
     Athena
    4.27
     Alex
    4.25
     Anton
    4.18
     Zeus
    4.18
    Act Density 0.007%

    No Known Activations