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

    Neuronpedia

    INDEX
    Explanations

    terms related to race, especially the comparison between whites and minorities

    oai_token-act-pair · gpt-3.5-turbo

    references to racial groups, particularly focusing on whites and blacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ground
    -0.70
    ãĤº
    -0.69
    ãĤ¯
    -0.66
     Himal
    -0.63
     Suzuki
    -0.62
    Bird
    -0.62
     Horse
    -0.62
     liability
    -0.62
    inventoryQuantity
    -0.62
     Chaser
    -0.62
    POSITIVE LOGITS
    ervative
    0.98
    folk
    0.88
    paces
    0.88
    pace
    0.84
    aurus
    0.84
    kees
    0.82
    ophone
    0.82
    merce
    0.81
    ktop
    0.80
    xual
    0.79
    Act Density 0.024%

    No Known Activations