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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1420
    Prev
    Next
    INDEX
    Explanations

    performance statistics related to points and runs allowed in sports 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
    aptic
    -0.76
     formulated
    -0.76
     voiced
    -0.71
     PROGRAM
    -0.71
     risked
    -0.69
    cycl
    -0.68
    cussion
    -0.66
     addressed
    -0.66
     provision
    -0.66
    eatured
    -0.65
    POSITIVE LOGITS
    AST
    0.73
     Empire
    0.68
     none
    0.66
    haven
    0.66
    ast
    0.65
     Sakuya
    0.63
    none
    0.63
    aster
    0.62
     Aur
    0.62
    other
    0.61
    Activations Density 0.083%

    No Known Activations