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. 8-TRES-DC
    5. 204
    Prev
    Next
    INDEX
    Explanations

    structured numerical references or citations

    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
     navigating
    -0.64
     mills
    -0.59
    ousel
    -0.59
     reclaim
    -0.59
     gearing
    -0.57
     parks
    -0.57
     undo
    -0.56
    odon
    -0.56
     unlocking
    -0.55
     travers
    -0.55
    POSITIVE LOGITS
    ],[
    0.82
    ]-
    0.68
    )--
    0.66
    �醒
    0.66
    .]
    0.65
    .>>
    0.65
    -.
    0.65
     ESV
    0.65
    !/
    0.64
    >"
    0.64
    Activations Density 0.179%

    No Known Activations