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

    Neuronpedia

    INDEX
    Explanations

    references to political discussions and investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    201
    -0.29
    usterity
    -0.25
     Obama
    -0.25
    Obama
    -0.24
     tweeted
    -0.23
     tweet
    -0.22
    Û²Û°Û±
    -0.22
     tweeting
    -0.20
     twitter
    -0.20
     Trump
    -0.20
    POSITIVE LOGITS
     Bush
    0.40
    Bush
    0.37
     bush
    0.31
     Iraq
    0.28
     Iraqi
    0.25
    Iraq
    0.23
     Cheney
    0.23
     Saddam
    0.21
     Kyoto
    0.21
     Abu
    0.21
    Act Density 0.036%

    No Known Activations