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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific ethnic groups, possibly within a societal or political context

    oai_token-act-pair · gpt-3.5-turbo

    mentions of ethnic groups and discussions surrounding ethnicity-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uden
    -0.92
    tower
    -0.88
    aday
    -0.87
    agher
    -0.80
    aunder
    -0.78
    ertodd
    -0.74
    etheus
    -0.72
    doors
    -0.71
    ocket
    -0.71
    20439
    -0.70
    POSITIVE LOGITS
     cleansing
    1.19
     minorities
    1.09
    ities
    1.05
     minority
    0.90
     slurs
    0.83
     appropriation
    0.82
    ethnic
    0.79
     affiliation
    0.79
     backgrounds
    0.79
     supremacists
    0.79
    Act Density 0.026%

    No Known Activations