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

    Neuronpedia

    INDEX
    Explanations

    statements related to political actions and policies

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicative of political rhetoric and controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç·
    -0.80
    pure
    -0.80
    geist
    -0.79
     tremend
    -0.78
    upe
    -0.77
    fuck
    -0.75
    gru
    -0.73
    lol
    -0.73
    greg
    -0.73
    ileged
    -0.73
    POSITIVE LOGITS
     lawmakers
    1.22
     MPs
    1.12
     Treasury
    1.10
     President
    1.10
     campaigners
    1.09
     Congress
    1.09
     diplomats
    1.05
     Attorney
    1.05
     negotiators
    1.05
     officials
    1.05
    Act Density 0.717%

    No Known Activations