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

    Neuronpedia

    INDEX
    Explanations

    mentions of political conservatism

    oai_token-act-pair · gpt-3.5-turbo

    references to conservative ideologies and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amaz
    -0.82
    fleet
    -0.81
    RIP
    -0.77
    chest
    -0.76
    agram
    -0.74
    WIND
    -0.72
    upon
    -0.71
     Marathon
    -0.70
    oa
    -0.69
    ĸļ
    -0.69
    POSITIVE LOGITS
     conservatives
    0.90
     egalitarian
    0.88
     orthodoxy
    0.88
     conservative
    0.87
     evangelical
    0.86
    atism
    0.85
     conservatism
    0.83
     fringe
    0.81
     leaning
    0.81
     republican
    0.80
    Act Density 0.017%

    No Known Activations