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

    Neuronpedia

    INDEX
    Explanations

    discussions about political systems or power dynamics

    oai_token-act-pair · gpt-3.5-turbo

    references to political power dynamics and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cade
    -0.79
     :=
    -0.77
     Photograph
    -0.76
    cross
    -0.74
    together
    -0.74
    ItemImage
    -0.73
    NH
    -0.73
    tackle
    -0.72
    iden
    -0.69
    icably
    -0.68
    POSITIVE LOGITS
     whims
    1.09
     superiors
    1.02
     elites
    1.01
     bureaucrats
    1.01
     Almighty
    1.01
     lords
    0.94
     rulers
    0.92
     masters
    0.92
     incompetent
    0.88
     imagination
    0.88
    Act Density 0.531%

    No Known Activations