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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and legislative roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     senator
    -0.20
     Senators
    -0.20
    steder
    -0.19
     Senator
    -0.18
     senators
    -0.18
    Senator
    -0.18
    _executor
    -0.17
     Bis
    -0.17
     bis
    -0.16
    bis
    -0.16
    POSITIVE LOGITS
     Minority
    0.34
     Speaker
    0.34
     Leader
    0.34
     speaker
    0.33
     Majority
    0.33
     minority
    0.32
     majority
    0.31
     leadership
    0.30
     leader
    0.30
    Speaker
    0.29
    Act Density 0.038%

    No Known Activations