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

    Neuronpedia

    INDEX
    Explanations

    specific references to political figures, specifically Vice Presidents and Presidents

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures, specifically Vice Presidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mos
    -0.66
     goats
    -0.62
     Pwr
    -0.62
     cows
    -0.60
     plate
    -0.59
     exting
    -0.58
    bane
    -0.56
     foll
    -0.56
     magnitude
    -0.56
     estab
    -0.56
    POSITIVE LOGITS
     Biden
    1.06
    OTUS
    0.94
     Cheney
    0.80
     Gore
    0.75
    owitz
    0.74
    president
    0.73
    vir
    0.71
     Lyndon
    0.70
    communications
    0.70
     Pence
    0.69
    Act Density 0.047%

    No Known Activations