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

    Neuronpedia

    INDEX
    Explanations

    titles or headings for articles or publications

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "article."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    creen
    -0.86
    cffff
    -0.79
     palate
    -0.77
    ²¾
    -0.76
    elsius
    -0.73
    bered
    -0.72
    gettable
    -0.72
    omething
    -0.67
    sembly
    -0.66
    ascus
    -0.66
    POSITIVE LOGITS
     article
    1.09
     articles
    1.04
     ARTICLE
    0.90
    Article
    0.78
    ¶
    0.77
     Articles
    0.75
    RFC
    0.74
     Article
    0.72
    article
    0.71
    ###
    0.71
    Act Density 0.021%

    No Known Activations