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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     senator
    -0.18
    ifik
    -0.15
     Senator
    -0.15
     гÑĥбеÑĢ
    -0.15
    Senator
    -0.15
    gra
    -0.15
    iku
    -0.14
    bish
    -0.14
     senators
    -0.14
     Senators
    -0.14
    POSITIVE LOGITS
     Minority
    0.38
     Speaker
    0.37
     speaker
    0.33
     minority
    0.33
    Speaker
    0.32
     Majority
    0.32
     Leader
    0.32
     Speakers
    0.31
     majority
    0.29
     Whip
    0.29
    Act Density 0.029%

    No Known Activations