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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and events, especially related to presidents and elections

    oai_token-act-pair · gpt-3.5-turbo

    references to political leaders and presidential contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maxwell
    -0.87
    Scot
    -0.81
     Midwest
    -0.74
     Whitney
    -0.73
     Kear
    -0.73
     AOL
    -0.70
     Trout
    -0.69
     Drake
    -0.69
     advertisers
    -0.69
     Rockefeller
    -0.67
    POSITIVE LOGITS
     Mahmoud
    1.08
     Bashar
    0.99
    rar
    0.87
    ÄŁ
    0.87
    sein
    0.86
    È
    0.84
    avi
    0.84
     assassinated
    0.83
     elections
    0.81
     Kiev
    0.80
    Act Density 0.227%

    No Known Activations