© 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. 1295
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation marks, primarily periods

    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
    icans
    -0.65
    eds
    -0.62
     clash
    -0.60
     ascend
    -0.60
    ricanes
    -0.59
     surf
    -0.57
    enberg
    -0.56
    lander
    -0.56
    luent
    -0.56
     flush
    -0.56
    POSITIVE LOGITS
     .
    0.83
    etheless
    0.71
     ."
    0.69
      
    0.68
    �
    0.67
    DonaldTrump
    0.66
    �
    0.65
    �
    0.65
    �
    0.64
    �
    0.64
    Activations Density 0.031%

    No Known Activations