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

    Neuronpedia

    INDEX
    Explanations

    references to racial identity, particularly focusing on the Black community

    oai_token-act-pair · gpt-3.5-turbo

    references to racial issues and the experiences of Black individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Station
    -0.76
    illin
    -0.73
    TI
    -0.71
    TOP
    -0.71
    Tro
    -0.70
    _-
    -0.69
    isner
    -0.68
    UTERS
    -0.67
    atre
    -0.66
    tenance
    -0.66
    POSITIVE LOGITS
     blacks
    1.17
     whites
    1.01
     Blacks
    0.86
     Hispanics
    0.82
    acks
    0.73
     hust
    0.72
     negro
    0.71
    xual
    0.71
     Africans
    0.70
     riots
    0.70
    Act Density 0.013%

    No Known Activations