© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1878
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas and question marks

    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
    wikipedia
    -0.81
     ILCS
    -0.78
    BuyableInstoreAndOnline
    -0.76
    ffff
    -0.71
    wik
    -0.69
    aundering
    -0.68
    光
    -0.66
    gif
    -0.66
    ilitary
    -0.66
    Footnote
    -0.66
    POSITIVE LOGITS
     swipe
    0.66
    iversary
    0.64
     readiness
    0.64
     landfall
    0.62
    ounce
    0.60
     conjunction
    0.59
     introductory
    0.58
     preview
    0.58
     Tablet
    0.57
     later
    0.57
    Activations Density 0.009%

    No Known Activations