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

    Neuronpedia

    INDEX
    Explanations

    words related to government officials and political leaders, especially presidents and prime ministers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    MpServer
    -0.73
    selves
    -0.70
     [];
    -0.66
    é¾
    -0.66
    Medium
    -0.63
    esville
    -0.62
    crew
    -0.62
    rawdownloadcloneembedreportprint
    -0.62
    kinson
    -0.61
     misc
    -0.61
    POSITIVE LOGITS
     Vladimir
    0.87
     Francois
    0.83
     Angela
    0.83
     Bashar
    0.82
     Vlad
    0.82
     Boris
    0.82
    avi
    0.80
     Sheikh
    0.79
     Sergio
    0.79
     Recep
    0.78
    Act Density 0.123%

    No Known Activations