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

    Neuronpedia

    INDEX
    Explanations

    mentions of political leadership roles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political leaders, specifically presidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maxwell
    -0.78
     strangers
    -0.70
    hovah
    -0.69
    asca
    -0.69
    opter
    -0.67
    aughs
    -0.64
     brim
    -0.63
    kinson
    -0.63
    oken
    -0.62
    ogene
    -0.62
    POSITIVE LOGITS
     Mahmoud
    1.02
     Bashar
    0.95
     Jinping
    0.92
     Mahm
    0.91
     Francois
    0.84
     Tayyip
    0.83
     Petro
    0.82
     Recep
    0.78
     Hassan
    0.78
     François
    0.77
    Act Density 0.098%

    No Known Activations