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

    Neuronpedia

    INDEX
    Explanations

    the word "Speaker" followed by a name or position

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political figures, specifically speakers of the House

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arial
    -0.80
    urat
    -0.72
     Belarus
    -0.68
     Mines
    -0.64
     Devils
    -0.62
     mines
    -0.58
    kus
    -0.58
    ties
    -0.57
    sters
    -0.57
     Mining
    -0.57
    POSITIVE LOGITS
    phone
    0.94
     Newt
    0.84
    Ryan
    0.83
     speaker
    0.83
     Boehner
    0.80
    NetMessage
    0.79
    woman
    0.78
     Gingrich
    0.77
    hip
    0.75
    person
    0.73
    Act Density 0.050%

    No Known Activations