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

    Neuronpedia

    INDEX
    Explanations

    specific social identities and characteristics, particularly those related to gender, race, and cognitive performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.04
    2:0.15
    3:0.06
    4:0.03
    5:0.04
    6:0.06
    7:0.10
    8:0.20
    9:0.07
    10:0.07
    11:0.09
    Negative Logits
     ensued
    -1.36
     teamed
    -1.25
     shone
    -1.19
     hadn
    -1.16
     didnt
    -1.14
     lasted
    -1.14
     trailed
    -1.13
     proceeded
    -1.11
    arthed
    -1.09
     opted
    -1.04
    POSITIVE LOGITS
     extremes
    1.31
     specificity
    1.29
     constituents
    1.26
    erning
    1.18
    覚醒
    1.15
    Region
    1.12
    traditional
    1.08
     origin
    1.03
     Mothers
    1.03
     totality
    1.03
    Act Density 0.070%

    No Known Activations