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

    Neuronpedia

    INDEX
    Explanations

    mentions of racial identities, specifically related to 'white' and associated terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    white, color and concept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.73
    ValueStyle
    -0.63
    tagHelperRunner
    -0.57
    AddHtmlAttribute
    -0.54
    RegistryLite
    -0.54
    Tikang
    -0.53
     resourceCulture
    -0.52
     Photocase
    -0.52
    (!__
    -0.51
     ويكيپيديا
    -0.50
    POSITIVE LOGITS
     White
    1.46
     white
    1.43
    White
    1.41
     WHITE
    1.35
    white
    1.33
    WHITE
    1.26
     whites
    1.09
    白
    1.05
     Whites
    1.05
     whiteness
    1.03
    Act Density 0.023%

    No Known Activations