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

    Neuronpedia

    INDEX
    Explanations

    hyperlinks and website addresses

    oai_token-act-pair · gpt-3.5-turbo

    URLs and links to social media pages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertation
    -0.69
     Pyramid
    -0.69
     pandemonium
    -0.69
     pie
    -0.69
     jar
    -0.68
     deserts
    -0.68
     pyramid
    -0.67
     illustrated
    -0.66
     courtesy
    -0.64
     labyrinth
    -0.62
    POSITIVE LOGITS
    groups
    1.27
    pages
    1.00
    DonaldTrump
    0.96
    involved
    0.95
    events
    0.91
    realDonaldTrump
    0.88
    uncle
    0.83
    intent
    0.82
    watch
    0.79
    fw
    0.79
    Act Density 0.031%

    No Known Activations