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

    references to "coup" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wealth
    -0.80
    Account
    -0.75
    Pract
    -0.73
     Pv
    -0.71
     Nationwide
    -0.70
    ************
    -0.70
    Export
    -0.69
    Av
    -0.69
    ________
    -0.67
     Origin
    -0.66
    POSITIVE LOGITS
     coup
    1.23
    unta
    0.86
     intrigue
    0.84
     overthrow
    0.83
     toppled
    0.82
     indu
    0.81
     topple
    0.80
    ilus
    0.79
    oup
    0.76
     overth
    0.76
    Act Density 0.007%

    No Known Activations