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

    Neuronpedia

    INDEX
    Explanations

    references to political coups

    oai_token-act-pair · gpt-3.5-turbo

    mentions of coup attempts or related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ£
    -0.78
     Wealth
    -0.75
    Scot
    -0.72
     Pv
    -0.69
    Ocean
    -0.69
    Alpha
    -0.68
     Nationwide
    -0.67
     Grail
    -0.66
    Merit
    -0.66
    Travel
    -0.66
    POSITIVE LOGITS
    unta
    1.00
     coup
    0.95
     toppled
    0.86
     attempt
    0.84
     overthrow
    0.83
     overth
    0.83
     insurrection
    0.82
     plot
    0.79
    oup
    0.78
     revolt
    0.77
    Act Density 0.026%

    No Known Activations