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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 9-TRES-DC
    5. 674
    Prev
    Next
    INDEX
    Explanations

    references to news publications, specifically "The Washington Post" and "The Seattle Times"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oxide
    -0.73
    ribune
    -0.65
    Scroll
    -0.63
    Age
    -0.62
    ogan
    -0.62
     Times
    -0.62
    Times
    -0.60
    Contents
    -0.60
    News
    -0.60
    Rus
    -0.60
    POSITIVE LOGITS
    legal
    0.67
    untled
    0.67
    cific
    0.65
    olate
    0.62
     サーティワン
    0.61
     Converted
    0.61
    killed
    0.61
    ertodd
    0.60
     Canaver
    0.59
    soever
    0.59
    Activations Density 0.019%

    No Known Activations