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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships or connections between topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ведÑĮ
    -0.15
     вк
    -0.14
     باÙĤ
    -0.14
    -summary
    -0.14
    orpor
    -0.14
    ë£Į
    -0.13
    ิà¹Ĥล
    -0.13
     Demir
    -0.13
    _VARS
    -0.13
    owie
    -0.13
    POSITIVE LOGITS
     stories
    0.28
     Stories
    0.24
     articles
    0.23
     story
    0.22
    RELATED
    0.21
     posts
    0.21
     Related
    0.21
     Articles
    0.21
     coverage
    0.21
     related
    0.20
    Act Density 0.019%

    No Known Activations