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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 469
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation that signify the end of statements or questions

    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
     teasp
    -0.85
    iosyn
    -0.72
     サーティワン
    -0.72
    thumbnails
    -0.72
    ipolar
    -0.72
     untreated
    -0.70
     envelope
    -0.70
    �
    -0.69
     sidx
    -0.69
     foil
    -0.69
    POSITIVE LOGITS
     Continuing
    0.73
    Secondly
    0.70
    But
    0.68
    However
    0.66
    Below
    0.65
     But
    0.64
    By
    0.64
     Secondly
    0.63
     Katy
    0.63
     Mods
    0.62
    Activations Density 0.068%

    No Known Activations