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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures, particularly House Speakers

    oai_token-act-pair · gpt-3.5-turbo

    references to the role or position of the House Speaker

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eros
    -0.80
    schild
    -0.70
    arial
    -0.69
    kus
    -0.68
    ibaba
    -0.67
    kinson
    -0.66
    ter
    -0.64
     sled
    -0.63
    zl
    -0.61
    tering
    -0.61
    POSITIVE LOGITS
     Speaker
    0.90
     speaker
    0.87
     Newt
    0.79
    person
    0.78
     laureate
    0.76
    loo
    0.76
    ħĭ
    0.75
     Gingrich
    0.74
    woman
    0.72
    phone
    0.70
    Act Density 0.011%

    No Known Activations