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

    Neuronpedia

    INDEX
    Explanations

    topics related to diversity, equity, and inclusion initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilde
    -0.16
    abler
    -0.14
    ÑĨÑİ
    -0.14
    NewProp
    -0.13
    /MPL
    -0.12
    azzi
    -0.12
     Terraria
    -0.12
    à¤Łà¤ķ
    -0.12
    _FAMILY
    -0.12
    itizen
    -0.12
    POSITIVE LOGITS
     Diversity
    0.43
     diversity
    0.41
     DE
    0.41
     unconscious
    0.35
     inclusion
    0.33
     racial
    0.32
     Bias
    0.31
     inclus
    0.30
     race
    0.30
     equity
    0.30
    Act Density 0.133%

    No Known Activations