© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 3073
    Prev
    Next
    INDEX
    Explanations

    references to sports events and outcomes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    riad
    -0.71
    roo
    -0.71
     Cosponsors
    -0.69
    asking
    -0.67
    ................................................................
    -0.66
    ugi
    -0.65
     footsteps
    -0.65
    query
    -0.64
     trem
    -0.63
    ersion
    -0.63
    POSITIVE LOGITS
     commer
    0.73
    ampions
    0.71
     playoff
    0.70
     sponsors
    0.69
     Carnegie
    0.68
     clin
    0.66
    ftime
    0.66
    pps
    0.64
     winners
    0.64
     SPORTS
    0.64
    Activations Density 0.112%

    No Known Activations