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

    Neuronpedia

    INDEX
    Explanations

    mentions of political coups

    oai_token-act-pair · gpt-3.5-turbo

    references to coups and coup attempts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ocean
    -0.73
     Wealth
    -0.73
    Travel
    -0.72
    ãĤ£
    -0.72
    english
    -0.70
    Pract
    -0.70
    Scot
    -0.69
    Medium
    -0.69
    Export
    -0.68
    Alpha
    -0.68
    POSITIVE LOGITS
     coup
    1.03
    unta
    0.95
     attempt
    0.88
     toppled
    0.87
     overthrow
    0.85
     ousted
    0.83
     overth
    0.83
     intrigue
    0.79
     revolt
    0.79
     plot
    0.78
    Act Density 0.021%

    No Known Activations