© 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. 1365
    Prev
    Next
    INDEX
    Explanations

    references to champions in various sports or competitions

    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
     lucky
    -0.88
    horn
    -0.75
    ══
    -0.74
    YS
    -0.71
    mania
    -0.70
    ν
    -0.70
    RY
    -0.70
    WIN
    -0.69
    OHN
    -0.68
    Winged
    -0.68
    POSITIVE LOGITS
     Ago
    0.76
     FG
    0.73
     Hurricanes
    0.72
     Ans
    0.70
     Continued
    0.70
     Anger
    0.70
     Deaths
    0.69
     Cutler
    0.67
     Interior
    0.66
     Sheen
    0.66
    Activations Density 0.097%

    No Known Activations