© 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. 1121
    Prev
    Next
    INDEX
    Explanations

    terms that indicate leadership or prominence in various fields or contexts

    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
    Buyable
    -0.72
     Commodore
    -0.70
    afety
    -0.69
     Fidel
    -0.68
    Official
    -0.67
    fleet
    -0.65
     Bryce
    -0.64
    bryce
    -0.62
     Important
    -0.62
     Franz
    -0.61
    POSITIVE LOGITS
    iled
    0.78
    tan
    0.67
     tan
    0.67
    icular
    0.67
    ao
    0.66
     arousal
    0.64
    ance
    0.63
    シャ
    0.63
    itte
    0.62
     edge
    0.61
    Activations Density 0.028%

    No Known Activations