© 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. 2066
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and 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
    rio
    -0.71
     FANTASY
    -0.69
    ibl
    -0.64
     CODE
    -0.64
    zzle
    -0.63
    ceivable
    -0.60
    ancial
    -0.60
    Directory
    -0.59
    RAFT
    -0.59
    arrell
    -0.59
    POSITIVE LOGITS
    Germany
    1.06
    Italy
    1.05
     Germany
    1.00
     Norway
    0.99
    Japan
    0.97
     Italy
    0.97
     Denmark
    0.96
     Greenland
    0.95
    Mexico
    0.94
     Scandinav
    0.94
    Activations Density 0.133%

    No Known Activations