© 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. 1298
    Prev
    Next
    INDEX
    Explanations

    references to time durations and scores in a game context

    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
    achine
    -0.77
    ャ
    -0.71
    ombo
    -0.70
    ersion
    -0.68
    ongyang
    -0.68
    igon
    -0.67
    ornia
    -0.67
    inton
    -0.67
    lins
    -0.65
    phia
    -0.63
    POSITIVE LOGITS
     Seller
    0.73
    xus
    0.66
     laureate
    0.65
     Sagan
    0.62
    ++++++++++++++++
    0.60
    )</
    0.58
     thereof
    0.58
     thanking
    0.58
     HH
    0.56
    ["
    0.56
    Activations Density 0.044%

    No Known Activations