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

    Neuronpedia

    INDEX
    Explanations

    instances where the text refers to ownership or association with someone's work or content

    oai_token-act-pair · gpt-3.5-turbo

    references to personal content and ownership in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uador
    -0.79
    uve
    -0.78
    ossibility
    -0.75
    cised
    -0.74
    cation
    -0.72
    endez
    -0.72
    factor
    -0.70
    igate
    -0.70
    FontSize
    -0.70
    imilation
    -0.70
    POSITIVE LOGITS
     writings
    1.29
     creations
    1.28
     work
    1.26
     videos
    1.25
     posts
    1.23
     publications
    1.16
     postings
    1.16
     articles
    1.14
     compositions
    1.12
     accomplishments
    1.12
    Act Density 0.256%

    No Known Activations