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

    Neuronpedia

    INDEX
    Explanations

    references to race and racial issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]='\
    -0.88
    sqm
    -0.85
    Pyx
    -0.82
     Sheets
    -0.81
    ETHING
    -0.79
    */;
    -0.78
     kasarigan
    -0.78
    Donovan
    -0.78
    surate
    -0.77
     Burnet
    -0.77
    POSITIVE LOGITS
     race
    1.64
     races
    1.54
     Race
    1.50
     RACE
    1.49
    Race
    1.44
     Races
    1.38
    race
    1.31
     Rac
    1.31
     racing
    1.25
    RACE
    1.19
    Act Density 0.088%

    No Known Activations