© 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. 3323
    Prev
    Next
    INDEX
    Explanations

    elements related to video game mechanics or statistics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     roundup
    -0.87
     srf
    -0.76
    ccording
    -0.74
     newcom
    -0.69
     challeng
    -0.69
     conflic
    -0.68
    gart
    -0.68
    ozy
    -0.67
     aggregation
    -0.66
    naissance
    -0.66
    POSITIVE LOGITS
    Constructed
    0.99
    inea
    0.87
    oral
    0.83
    Construction
    0.79
    Character
    0.79
    Acknowled
    0.75
    Materials
    0.74
    construct
    0.73
    moral
    0.69
    Diamond
    0.69
    Activations Density 0.220%

    No Known Activations