Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 629
    Prev
    Next
    INDEX
    Explanations

    recurring punctuation and connectors that indicate relationships or transitions in writing

    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
     Nightmares
    -0.50
     observer
    -0.46
     Pigs
    -0.45
     Anger
    -0.41
     Turtle
    -0.39
     Conversion
    -0.39
     Tune
    -0.39
     tune
    -0.39
     Convers
    -0.38
     Reaper
    -0.38
    POSITIVE LOGITS
    onym
    0.56
    ulo
    0.55
    ellen
    0.54
    ignt
    0.53
    paio
    0.53
    ntil
    0.53
    she
    0.52
    agame
    0.52
    apo
    0.52
    instead
    0.52
    Activations Density 0.967%

    No Known Activations