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

    Neuronpedia

    INDEX
    Explanations

    mentions of race or skin color, especially in discussions of discrimination and social issues

    oai_token-act-pair · gpt-3.5-turbo

    references to people of color and related discussions on social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EMS
    -0.82
    INGTON
    -0.82
    chn
    -0.79
    sonian
    -0.78
    ãĤ´
    -0.78
    sg
    -0.74
    pload
    -0.74
    CHA
    -0.74
    ERSON
    -0.73
    xon
    -0.73
    POSITIVE LOGITS
     slurs
    0.85
     minorities
    0.80
     backgrounds
    0.78
     communities
    0.76
     oppressed
    0.75
     flags
    0.72
    xual
    0.70
     queer
    0.70
     stereotypes
    0.69
     congreg
    0.68
    Act Density 0.017%

    No Known Activations