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

    Neuronpedia

    INDEX
    Explanations

    terms related to race and racial issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '))
    -0.88
    "])
    -0.81
     grève
    -0.76
    }),
    -0.75
     kasarigan
    -0.75
    outons
    -0.75
    TintMode
    -0.75
    bracht
    -0.75
    estias
    -0.73
     paroisse
    -0.73
    POSITIVE LOGITS
     race
    3.92
     Race
    3.56
    Race
    3.45
    race
    3.27
     races
    3.20
     RACE
    3.17
     Races
    2.81
    RACE
    2.75
    races
    2.57
     raced
    2.54
    Act Density 0.046%

    No Known Activations