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

    Neuronpedia

    INDEX
    Explanations

    terms related to race and discrimination

    oai_token-act-pair · gpt-3.5-turbo

    terms related to race and discrimination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocket
    -0.76
    soDeliveryDate
    -0.74
    ingen
    -0.74
    imar
    -0.73
    inventoryQuantity
    -0.73
    anmar
    -0.72
    issan
    -0.69
    UNE
    -0.68
    TOR
    -0.66
    urances
    -0.65
    POSITIVE LOGITS
     prejudice
    0.96
     Discrimination
    0.93
     ethnicity
    0.91
     ancestry
    0.88
     stereotyp
    0.86
     supremacist
    0.86
     discrimination
    0.82
     identity
    0.82
     slurs
    0.81
     prejudices
    0.80
    Act Density 0.106%

    No Known Activations