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

    Neuronpedia

    INDEX
    Explanations

    references to societal expectations and experiences related to motherhood, gender roles, and individual choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.18
    3:0.25
    4:0.11
    5:0.03
    6:0.03
    7:0.07
    8:0.04
    9:0.04
    10:0.09
    11:0.07
    Negative Logits
     FIRE
    -1.58
    tumblr
    -1.56
     Clockwork
    -1.46
     CALL
    -1.38
     Candy
    -1.37
     Cobra
    -1.36
     DRAGON
    -1.35
     Luther
    -1.34
     Seymour
    -1.32
     IRC
    -1.31
    POSITIVE LOGITS
     anymore
    2.85
     nor
    2.62
    nor
    1.68
     necessarily
    1.67
    Enough
    1.53
     slightest
    1.53
    ��
    1.50
    imilar
    1.50
    Orig
    1.50
     confir
    1.49
    Act Density 0.021%

    No Known Activations