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

    Neuronpedia

    INDEX
    Explanations

    references to political figures, specifically Presidents, in a critical context

    oai_token-act-pair · gpt-3.5-turbo

    references to the President

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MpServer
    -0.85
    rawdownloadcloneembedreportprint
    -0.85
    lot
    -0.81
    âĵĺ
    -0.72
     hitch
    -0.70
    lighting
    -0.68
    obyl
    -0.67
     rink
    -0.66
    TOR
    -0.66
    endish
    -0.66
    POSITIVE LOGITS
     Barack
    1.15
     Obama
    1.00
     Lyndon
    0.97
     Recep
    0.93
     Donald
    0.90
     Ronald
    0.87
     Dwight
    0.87
    ially
    0.85
     Bashar
    0.85
    ial
    0.85
    Act Density 0.041%

    No Known Activations