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

    Neuronpedia

    INDEX
    Explanations

    references to political coups or attempts

    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
     Neon
    -0.71
     Scotch
    -0.65
     Parenthood
    -0.64
     Wealth
    -0.62
     Trout
    -0.62
     Nationwide
    -0.62
     guiName
    -0.62
    HUD
    -0.62
     Gifts
    -0.60
     Voc
    -0.60
    POSITIVE LOGITS
     attempt
    1.07
    unta
    1.04
    oup
    1.00
     coup
    0.98
     plot
    0.94
     overth
    0.93
     overthrow
    0.92
    eering
    0.90
    vous
    0.89
    és
    0.85
    Act Density 0.068%

    No Known Activations