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

    Neuronpedia

    INDEX
    Explanations

    mentions of American politics

    oai_token-act-pair · gpt-3.5-turbo

    instances and discussions related to American politics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    val
    -0.83
    actory
    -0.80
    eret
    -0.77
    uran
    -0.77
    reek
    -0.75
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.75
    Interstitial
    -0.73
    ts
    -0.73
    amaz
    -0.72
    Companies
    -0.71
    POSITIVE LOGITS
     politics
    1.04
     correctness
    1.03
    eering
    0.90
    atism
    0.86
     Politics
    0.85
     intrig
    0.80
     ideology
    0.79
     lawy
    0.78
     realism
    0.77
    jriwal
    0.77
    Act Density 0.012%

    No Known Activations