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. 368
    Prev
    Next
    INDEX
    Explanations

    HTML tags and formatting attributes

    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
    bara
    -0.87
    ization
    -0.74
    arten
    -0.69
    glers
    -0.65
    pled
    -0.63
    ibaba
    -0.63
    ific
    -0.62
    jamin
    -0.62
    psey
    -0.61
    agents
    -0.60
    POSITIVE LOGITS
    Introduced
    0.72
    ↑
    0.71
    [[
    0.69
     VIEW
    0.65
     Originally
    0.63
    Rum
    0.63
     ',
    0.63
    ヴ
    0.63
    League
    0.63
    Missing
    0.63
    Activations Density 0.068%

    No Known Activations