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

    Neuronpedia

    INDEX
    Explanations

    references to race, particularly focusing on white individuals and their societal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FormTagHelper
    -0.94
    NameInMap
    -0.88
    })`
    -0.85
     henvisninger
    -0.85
    /*
    -0.82
     NCC
    -0.81
     SLP
    -0.79
     betweenstory
    -0.78
     onOptions
    -0.75
    ']").
    -0.74
    POSITIVE LOGITS
     White
    1.60
    White
    1.44
    WHITE
    1.35
     WHITE
    1.35
     Whites
    1.30
     white
    1.26
    white
    1.23
    Whites
    1.19
    WhiteSpace
    1.18
     Whitehead
    1.16
    Act Density 0.054%

    No Known Activations