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

    Neuronpedia

    INDEX
    Explanations

    mentions of political leaders, specifically presidents

    oai_token-act-pair · gpt-3.5-turbo

    references to political leaders and their titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nadu
    -0.79
    atown
    -0.76
    MpServer
    -0.76
     precincts
    -0.74
     Peaks
    -0.69
    halla
    -0.69
     Ukrain
    -0.68
    yssey
    -0.62
    utterstock
    -0.61
     acupuncture
    -0.61
    POSITIVE LOGITS
     Nicolas
    0.90
     Francois
    0.89
     Bashar
    0.88
     Nicol
    0.86
     Tayyip
    0.84
     Barack
    0.81
     François
    0.80
     Mahmoud
    0.79
     Michel
    0.78
     Nurs
    0.77
    Act Density 0.076%

    No Known Activations