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

    Neuronpedia

    INDEX
    Explanations

    mentions or contexts related to political regimes

    oai_token-act-pair · gpt-3.5-turbo

    references to political regimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lent
    -0.84
    eting
    -0.82
    sight
    -0.79
    furt
    -0.76
    Redd
    -0.76
    ritch
    -0.75
    ths
    -0.75
    lder
    -0.74
     Blessed
    -0.73
     Edinburgh
    -0.73
    POSITIVE LOGITS
     regimes
    0.99
     regime
    0.97
     dictators
    0.84
     dictator
    0.84
     prosec
    0.83
     imposed
    0.82
     dictatorship
    0.82
     overth
    0.81
     overthrow
    0.81
     unilaterally
    0.78
    Act Density 0.012%

    No Known Activations