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

    Neuronpedia

    INDEX
    Explanations

    terms related to racial identities and racial discrimination

    oai_token-act-pair · gpt-3.5-turbo

    references to race and ethnicity in the context of discrimination and social justice issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erva
    -0.90
    unction
    -0.85
    cit
    -0.83
    ows
    -0.76
    irs
    -0.76
     Mub
    -0.74
    uden
    -0.74
    odder
    -0.73
    iaries
    -0.72
    anmar
    -0.72
    POSITIVE LOGITS
     Equality
    0.91
    course
    0.90
    blind
    0.82
     Discrimination
    0.80
    horse
    0.78
    boat
    0.76
     slurs
    0.76
    Race
    0.75
    Menu
    0.74
     race
    0.73
    Act Density 0.018%

    No Known Activations