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 political coups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ring
    -0.66
    WM
    -0.65
    eth
    -0.63
    Store
    -0.62
     Spectrum
    -0.62
     Sm
    -0.62
     Dev
    -0.62
    ->
    -0.62
     Shelter
    -0.61
    NN
    -0.60
    POSITIVE LOGITS
     coup
    3.88
     Coup
    2.06
     revolt
    1.26
     takeover
    1.25
     overthrow
    1.24
     cou
    1.22
     insurrection
    1.22
     assassination
    1.18
     dictatorship
    1.18
     revolution
    1.16
    Act Density 0.014%

    No Known Activations