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

    Neuronpedia

    INDEX
    Explanations

    mentions of the Dalai Lama and related Tibetan political context

    oai_token-act-pair · gpt-3.5-turbo

    references to the Dalai Lama and Tibetan Buddhism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hitchcock
    -0.71
    ardon
    -0.67
    umbers
    -0.67
    etting
    -0.65
    ptroller
    -0.65
    adden
    -0.65
     Hurricanes
    -0.63
    agents
    -0.63
    nesota
    -0.62
    nect
    -0.62
    POSITIVE LOGITS
     Lama
    1.40
     Dalai
    0.97
     Buddhism
    0.92
     Buddhist
    0.91
     monks
    0.89
     Tibet
    0.85
    utan
    0.84
     Tibetan
    0.84
     Jinping
    0.79
     Buddh
    0.75
    Act Density 0.020%

    No Known Activations