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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 316
    Prev
    Next
    INDEX
    Explanations

    terms and references related to specific measurements or parameters in a context that seems technical or numerical

    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
    opoulos
    -0.65
     Sparrow
    -0.64
     Sven
    -0.62
    aeus
    -0.60
     Mori
    -0.60
    kell
    -0.58
     Hugo
    -0.58
     Constantin
    -0.58
     Vance
    -0.57
     Kaplan
    -0.57
    POSITIVE LOGITS
    shop
    0.81
    EngineDebug
    0.79
    ship
    0.71
    docker
    0.71
    ners
    0.65
    �
    0.65
    ships
    0.64
    rats
    0.64
    sets
    0.64
    sites
    0.64
    Activations Density 1.583%

    No Known Activations