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

    Neuronpedia

    INDEX
    Explanations

    terms related to racial issues and discrimination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    átil
    -0.60
    tasche
    -0.59
     Ambition
    -0.59
    akyti
    -0.56
    SEGUIR
    -0.56
    цезда
    -0.55
    icata
    -0.54
     désolés
    -0.54
    بوابة
    -0.54
     Baillargeon
    -0.54
    POSITIVE LOGITS
     racial
    1.37
     racially
    1.30
    Racism
    1.25
     Racial
    1.25
     racism
    1.24
     Racism
    1.20
     racist
    1.19
    racial
    1.16
    racist
    1.05
    racism
    1.01
    Act Density 0.439%

    No Known Activations