© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 3221
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and section headings in a document

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    pring
    -0.69
    版
    -0.69
    yssey
    -0.68
     leaps
    -0.63
     whence
    -0.62
     leap
    -0.62
    hunter
    -0.60
    .}
    -0.60
    orie
    -0.59
    chu
    -0.58
    POSITIVE LOGITS
     Amid
    0.72
     Occasionally
    0.69
     Several
    0.69
     Dirt
    0.68
     Although
    0.67
     Divide
    0.66
     Papers
    0.66
     Perhaps
    0.65
     Students
    0.64
     While
    0.63
    Activations Density 0.013%

    No Known Activations