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

    Neuronpedia

    INDEX
    Explanations

    terms related to authoritarianism and totalitarianism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to authoritarianism and totalitarianism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovember
    -0.90
    ttp
    -0.86
     Tire
    -0.86
    WAYS
    -0.76
    Render
    -0.75
    llo
    -0.74
    src
    -0.73
    FORE
    -0.73
    EVA
    -0.73
    points
    -0.71
    POSITIVE LOGITS
     totalitarian
    1.23
     regimes
    1.18
     authoritarian
    1.17
     dictatorship
    1.14
     tyranny
    1.05
     dictators
    1.01
     dictator
    1.01
     ideology
    0.94
     dystop
    0.94
     bureaucr
    0.92
    Act Density 0.021%

    No Known Activations