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. 176
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation, specifically commas

    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
    ades
    -0.79
    iquette
    -0.74
    adian
    -0.73
    mere
    -0.72
    ocy
    -0.71
    adia
    -0.71
    status
    -0.69
    ENTS
    -0.69
    oms
    -0.68
    神
    -0.67
    POSITIVE LOGITS
     which
    1.48
     whose
    1.25
    which
    1.19
     wherein
    1.14
     whom
    1.10
     Which
    1.03
     whereby
    1.02
     whence
    0.96
     where
    0.93
    Which
    0.93
    Activations Density 0.325%

    No Known Activations