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

    Neuronpedia

    INDEX
    Explanations

    topics related to bias and discrimination, especially in the context of gender and race

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.13
    1:0.04
    2:0.14
    3:0.06
    4:0.05
    5:0.04
    6:0.18
    7:0.04
    8:0.04
    9:0.20
    10:0.03
    11:0.02
    Negative Logits
     Mortal
    -3.23
     Turtles
    -3.21
     lease
    -3.19
     LU
    -3.16
    APTER
    -3.15
    LU
    -3.15
     Evan
    -3.11
    VC
    -3.10
     Pett
    -3.08
    aiden
    -3.07
    POSITIVE LOGITS
     bias
    7.80
     biases
    7.33
     biased
    7.11
    biased
    6.48
     prejudices
    5.40
     prejud
    5.35
     unbiased
    4.92
     prejudice
    4.87
     skew
    4.68
     skewed
    4.49
    Act Density 0.004%

    No Known Activations