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

    Neuronpedia

    INDEX
    Explanations

    references to political ideologies, specifically socialism

    oai_token-act-pair · gpt-3.5-turbo

    references to socialism and related ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubi
    -0.73
     trainers
    -0.68
     OD
    -0.68
     onboard
    -0.66
    eri
    -0.65
    ocket
    -0.65
     pads
    -0.64
    tail
    -0.64
     processing
    -0.63
     mer
    -0.62
    POSITIVE LOGITS
     Socialist
    3.98
     Socialism
    2.35
     socialist
    2.34
     socialists
    1.90
     Communist
    1.71
     Marxist
    1.67
     socialism
    1.63
     Bolshevik
    1.48
     communist
    1.45
     Trotsky
    1.45
    Act Density 0.018%

    No Known Activations