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

    Neuronpedia

    INDEX
    Explanations

    references to conservative ideologies or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to conservatives and their political behavior or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WAY
    -0.71
    fleet
    -0.69
    Ship
    -0.69
    Variable
    -0.67
    BY
    -0.64
    amaz
    -0.64
    FORE
    -0.64
    Owner
    -0.62
    INS
    -0.62
    operation
    -0.62
    POSITIVE LOGITS
    ervative
    1.18
    ervatives
    1.05
    atism
    0.93
     Protestants
    0.81
     leaning
    0.80
     orthodoxy
    0.77
     radicals
    0.74
     conservatives
    0.74
     bashing
    0.73
    men
    0.72
    Act Density 0.013%

    No Known Activations