© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 913
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connectors that indicate relationships between phrases or clauses

    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
    range
    -0.73
    ️
    -0.69
    loads
    -0.67
    alert
    -0.66
    safe
    -0.65
    fired
    -0.62
    self
    -0.62
    hani
    -0.61
    campus
    -0.60
    guard
    -0.60
    POSITIVE LOGITS
    icter
    0.65
     congr
    0.62
     Highest
    0.62
     �
    0.62
     Detected
    0.60
     abolish
    0.56
     Clash
    0.55
     guiActiveUn
    0.55
     Ibid
    0.55
     Breaking
    0.54
    Activations Density 0.311%

    No Known Activations