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

    Neuronpedia

    INDEX
    Explanations

    references to women in various contexts, particularly in age-related or relational situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.01
    2:0.15
    3:0.06
    4:0.12
    5:0.03
    6:0.08
    7:0.02
    8:0.15
    9:0.05
    10:0.10
    11:0.10
    Negative Logits
    Reloaded
    -1.31
    eries
    -1.22
     smoot
    -1.20
    Ware
    -1.18
    Rules
    -1.18
     Hazard
    -1.17
     「
    -1.16
     Limit
    -1.16
     Deposit
    -1.15
     where
    -1.14
    POSITIVE LOGITS
    kinson
    1.55
    dinand
    1.54
     alike
    1.42
    rolet
    1.41
     gunman
    1.41
     Kazakh
    1.37
    ullah
    1.36
    olulu
    1.34
    duino
    1.33
    azeera
    1.33
    Act Density 0.020%

    No Known Activations