© 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
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 477
    Prev
    Next
    INDEX
    Explanations

    instances of sentence-ending punctuation

    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
     "$:/
    -0.63
     eject
    -0.61
    rup
    -0.60
     crash
    -0.59
     endeavour
    -0.59
     compulsion
    -0.59
    IGH
    -0.59
     neutron
    -0.58
     punishment
    -0.58
     excuse
    -0.58
    POSITIVE LOGITS
     Already
    0.75
    giving
    0.66
     Quite
    0.65
    Already
    0.64
    wr
    0.61
     Karin
    0.61
     Presumably
    0.59
     Cyn
    0.59
     Plot
    0.59
     Points
    0.58
    Activations Density 0.063%

    No Known Activations