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

    Neuronpedia

    INDEX
    Explanations

    mentions of political leaders and legislative positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kus
    -0.72
    eros
    -0.72
    arial
    -0.71
    uras
    -0.69
     sled
    -0.68
    schild
    -0.68
    ourced
    -0.67
    urat
    -0.67
    ibaba
    -0.65
    erial
    -0.62
    POSITIVE LOGITS
     Newt
    0.86
     Speaker
    0.85
    woman
    0.84
     Boehner
    0.82
    person
    0.77
     Gingrich
    0.76
    llan
    0.76
     speaker
    0.75
    ower
    0.73
     aide
    0.72
    Act Density 0.006%

    No Known Activations