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

    Neuronpedia

    INDEX
    Explanations

    mentions of the color white, especially in a social or political context

    oai_token-act-pair · gpt-3.5-turbo

    references to "white" in the context of race and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yrinth
    -1.08
    cffffcc
    -0.96
    ategory
    -0.87
    HCR
    -0.83
    rocal
    -0.80
    INGTON
    -0.79
    itual
    -0.77
    udeau
    -0.76
    Downloadha
    -0.76
    SIGN
    -0.76
    POSITIVE LOGITS
     supremacist
    1.39
     supremacists
    1.20
     supremacy
    1.04
     nationalist
    1.01
    bread
    1.00
     elephant
    0.94
     suprem
    0.89
    beard
    0.85
    house
    0.83
     male
    0.83
    Act Density 0.029%

    No Known Activations