© 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. 3176
    Prev
    Next
    INDEX
    Explanations

    instances of the word "played" and related gameplay statistics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    achine
    -0.83
    catentry
    -0.77
    agher
    -0.73
    nexus
    -0.73
    aceae
    -0.72
    ================================================================
    -0.71
    Definition
    -0.67
    sonian
    -0.67
    dust
    -0.67
    reet
    -0.67
    POSITIVE LOGITS
     adm
    0.78
     sparing
    0.63
     134
    0.63
     guard
    0.62
     reserve
    0.60
     154
    0.59
     pickup
    0.59
     cho
    0.59
    icer
    0.59
     anywhere
    0.59
    Activations Density 0.042%

    No Known Activations