© 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. 1498
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly 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
    ━
    -0.74
    ahime
    -0.67
    IP
    -0.66
     Legislation
    -0.65
    IDA
    -0.60
    Bang
    -0.60
     Palest
    -0.60
    oard
    -0.60
    eking
    -0.60
    itching
    -0.60
    POSITIVE LOGITS
     refers
    1.00
     discusses
    1.00
     believes
    1.00
     intends
    0.98
     relates
    0.96
     has
    0.93
     realizes
    0.93
     expects
    0.93
     considers
    0.92
     performs
    0.92
    Activations Density 0.156%

    No Known Activations