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

    Neuronpedia

    INDEX
    Explanations

    references to articles or sections in a document

    oai_token-act-pair · gpt-3.5-turbo

    the presence of article references in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     spawn
    -0.68
     pant
    -0.64
     Mann
    -0.64
     bats
    -0.63
     teleport
    -0.63
     elves
    -0.63
     magic
    -0.62
     blues
    -0.62
     dru
    -0.60
     MC
    -0.60
    POSITIVE LOGITS
    Article
    4.74
    article
    1.95
     Article
    1.92
    Newsletter
    1.69
     Articles
    1.57
     ARTICLE
    1.47
    Story
    1.42
    articles
    1.34
    advertisement
    1.33
    ICLE
    1.28
    Act Density 0.006%

    No Known Activations