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

    Neuronpedia

    INDEX
    Explanations

    identities and experiences related to race and ethnicity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alles
    -0.17
    ussy
    -0.16
    loquent
    -0.16
    vla
    -0.16
    olem
    -0.16
    jem
    -0.15
    OUNCE
    -0.15
    ghi
    -0.15
    aper
    -0.15
    (IServiceCollection
    -0.14
    POSITIVE LOGITS
     bir
    0.18
     non
    0.17
     white
    0.17
     races
    0.16
     African
    0.16
     dus
    0.15
     minority
    0.15
     Asian
    0.15
    Race
    0.15
     race
    0.15
    Act Density 0.191%

    No Known Activations