Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 99
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their roles or qualities within a group or society

    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
     VIDEOS
    -0.75
    ukemia
    -0.74
    enegger
    -0.66
    ctor
    -0.65
    rawdownloadcloneembedreportprint
    -0.64
    fore
    -0.63
    cross
    -0.63
    xon
    -0.62
    版
    -0.61
    cin
    -0.61
    POSITIVE LOGITS
     whose
    0.77
     where
    0.76
    idas
    0.69
     designed
    0.66
     containing
    0.61
     driven
    0.60
     that
    0.59
     Kear
    0.57
     whereby
    0.57
     covering
    0.56
    Activations Density 0.193%

    No Known Activations