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

    Neuronpedia

    INDEX
    Explanations

    references to racial dynamics and biases in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     consumers
    -0.14
     bÃło
    -0.14
    еле
    -0.14
    ë°Ģ
    -0.14
    ÃĸL
    -0.14
     Consumers
    -0.13
    USR
    -0.13
    thora
    -0.13
    LOUR
    -0.13
     consumer
    -0.12
    POSITIVE LOGITS
     firefighter
    0.41
     firefighters
    0.39
     Fire
    0.38
     fire
    0.34
    Fire
    0.34
     firefight
    0.33
    /fire
    0.30
    fire
    0.29
     FIRE
    0.29
    -fire
    0.28
    Act Density 0.003%

    No Known Activations