© 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. 1038
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific punctuation or formatting characters

    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
     Curve
    -0.71
     plus
    -0.70
     manoeuv
    -0.68
     circle
    -0.64
     curve
    -0.63
    ature
    -0.62
     calculations
    -0.61
     inadequate
    -0.61
     Kyoto
    -0.60
     forecast
    -0.60
    POSITIVE LOGITS
    aspx
    0.88
    pron
    0.86
    posted
    0.80
    Rh
    0.79
    Bus
    0.78
    エル
    0.77
    タ
    0.76
    edia
    0.76
    Similar
    0.75
    �
    0.73
    Activations Density 0.096%

    No Known Activations