© 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. 1081
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and their contextual significance in the text

    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
    xual
    -0.82
     pudding
    -0.80
     eleph
    -0.80
     tiss
    -0.79
     rul
    -0.76
    ensical
    -0.74
     rockets
    -0.72
     fireball
    -0.70
     recipes
    -0.70
     killer
    -0.70
    POSITIVE LOGITS
    Chief
    1.15
    Assistant
    1.14
    Speaking
    1.12
    Coun
    1.11
    SEE
    1.11
    Opp
    1.10
    Shape
    1.10
    Tap
    1.10
    Chair
    1.09
    Activ
    1.09
    Activations Density 0.283%

    No Known Activations