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, particularly military coups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ************
    -0.75
     Wealth
    -0.73
     Pv
    -0.72
    Av
    -0.71
    Pract
    -0.70
     Nationwide
    -0.70
    Account
    -0.70
    alone
    -0.68
    english
    -0.66
    ________
    -0.66
    POSITIVE LOGITS
     coup
    1.41
     intrigue
    0.89
     overthrow
    0.83
     assassination
    0.81
    unta
    0.81
     Coup
    0.81
    oup
    0.81
     topple
    0.79
     toppled
    0.78
     intrig
    0.78
    Act Density 0.005%

    No Known Activations