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. 616
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "comma" as a separator in various contexts

    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
    .(
    -0.84
    .
    -0.83
    .]
    -0.78
    .}
    -0.76
    ;
    -0.76
    .—
    -0.71
    :(
    -0.71
    .<
    -0.70
    .>>
    -0.70
    ,—
    -0.70
    POSITIVE LOGITS
    raltar
    0.61
    inventoryQuantity
    0.59
    ngth
    0.59
    uts
    0.57
    thumbnails
    0.57
    headers
    0.56
     concerts
    0.56
     scholarships
    0.55
    urdue
    0.53
    ecause
    0.52
    Activations Density 0.378%

    No Known Activations