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. 292
    Prev
    Next
    INDEX
    Explanations

    references to various media formats and release types

    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
     Osw
    -0.69
    ezvous
    -0.68
    tics
    -0.66
    anus
    -0.66
    ener
    -0.64
    mare
    -0.62
     Ernst
    -0.61
     Kelley
    -0.60
    oglu
    -0.60
    stru
    -0.60
    POSITIVE LOGITS
     appetite
    0.71
    [/
    0.69
    kered
    0.65
     worth
    0.65
    \'
    0.62
     0004
    0.61
    )</
    0.60
    .''.
    0.60
    itled
    0.60
    ikuman
    0.60
    Activations Density 0.051%

    No Known Activations