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. 666
    Prev
    Next
    INDEX
    Explanations

    references to Getty Images and associated contributors

    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
    "],
    -0.87
    ']
    -0.80
     guiName
    -0.78
    "}
    -0.77
    "},
    -0.73
    .]
    -0.72
    %]
    -0.70
     Conclusion
    -0.69
    "]
    -0.68
    .}
    -0.66
    POSITIVE LOGITS
    )—
    0.96
    )/
    0.77
    )].
    0.76
    )-
    0.74
    )
    0.70
    esm
    0.68
    )--
    0.62
    )*
    0.60
    )[
    0.60
     marches
    0.60
    Activations Density 0.147%

    No Known Activations