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

    Neuronpedia

    INDEX
    Explanations

    references to political regimes

    oai_token-act-pair · gpt-3.5-turbo

    references to political regimes or governments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lent
    -0.87
    sight
    -0.80
    ertodd
    -0.77
    furt
    -0.77
    Pokemon
    -0.75
    ritch
    -0.75
    ificantly
    -0.74
    Render
    -0.73
     Voy
    -0.72
    Ocean
    -0.71
    POSITIVE LOGITS
     regimes
    0.99
     regime
    0.99
     overthrow
    0.86
     dictatorship
    0.84
     dictator
    0.82
     milit
    0.81
     imposed
    0.81
     overth
    0.80
     dictators
    0.78
    archs
    0.77
    Act Density 0.024%

    No Known Activations