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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures, particularly presidents

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "President."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the title "President" before a proper name

    oai_token-act-pair · gpt-4-turbo
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.84
     exting
    -0.76
     hitch
    -0.73
    MpServer
    -0.72
    Sharp
    -0.72
    lot
    -0.70
     kindred
    -0.68
     +++
    -0.68
     sensit
    -0.66
    PsyNetMessage
    -0.66
    POSITIVE LOGITS
     Barack
    1.04
     Lyndon
    0.96
     President
    0.95
    ially
    0.93
     Obama
    0.91
     Donald
    0.91
     Dwight
    0.87
     Accountability
    0.86
     Mahmoud
    0.84
     Ronald
    0.83
    Act Density 0.040%

    No Known Activations