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

    Neuronpedia

    INDEX
    Explanations

    mentions of political races or competitions

    oai_token-act-pair · gpt-3.5-turbo

    the word "race" in various political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ushima
    -0.79
    ogle
    -0.75
    etheless
    -0.75
    ailability
    -0.74
    ricular
    -0.73
     Seym
    -0.70
     Wheat
    -0.68
    iar
    -0.68
    ectomy
    -0.67
    rolog
    -0.66
    POSITIVE LOGITS
    course
    1.13
    horse
    0.87
    manship
    0.86
    blind
    0.82
    goers
    0.80
     race
    0.79
    runners
    0.79
    cards
    0.79
     hust
    0.78
    ãĥ£
    0.76
    Act Density 0.015%

    No Known Activations