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

    Neuronpedia

    INDEX
    Explanations

    references to various groups of people or ethnicities

    oai_token-act-pair · gpt-3.5-turbo

    references to diverse human groups and communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LV
    -0.75
    SPONSORED
    -0.72
    zz
    -0.71
    QL
    -0.70
    ous
    -0.68
    CDC
    -0.67
    Phys
    -0.66
    VM
    -0.66
    RAY
    -0.66
    ctors
    -0.66
    POSITIVE LOGITS
     peoples
    1.23
    oples
    0.95
     nations
    0.82
    folk
    0.81
     minds
    0.81
     inhab
    0.79
    ĨĴ
    0.76
    ivities
    0.73
     dances
    0.72
    selves
    0.71
    Act Density 0.007%

    No Known Activations