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

    Neuronpedia

    INDEX
    Explanations

    phrases related to white supremacy and discrimination

    oai_token-act-pair · gpt-3.5-turbo

    references to white supremacist groups and ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fixed
    -0.77
    Glass
    -0.77
    MAC
    -0.72
    spring
    -0.72
    zl
    -0.71
    inet
    -0.71
    Bus
    -0.71
    Body
    -0.70
     Eyes
    -0.69
     Medium
    -0.67
    POSITIVE LOGITS
     guiActiveUn
    1.15
     supremacist
    1.05
     supremacists
    1.02
     suprem
    0.97
     sympath
    0.86
     prejudice
    0.79
    ervative
    0.78
     supremacy
    0.77
     referen
    0.77
    ervatives
    0.77
    Act Density 0.014%

    No Known Activations