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

    Neuronpedia

    INDEX
    Explanations

    disparities between genders or races in various aspects

    oai_token-act-pair · gpt-3.5-turbo

    references to gender and racial disparities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nikki
    -0.63
     Canaver
    -0.57
     revenge
    -0.55
     Wak
    -0.55
     RELE
    -0.55
     Kali
    -0.55
    Assembly
    -0.54
     vengeance
    -0.53
    arted
    -0.53
     IPM
    -0.53
    POSITIVE LOGITS
     counterparts
    0.80
     anymore
    0.77
    average
    0.71
     (âĪĴ
    0.71
    abouts
    0.71
     because
    0.70
    .
    0.69
    ().
    0.69
     [];
    0.69
    .[
    0.69
    Act Density 0.179%

    No Known Activations