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. 83
    Prev
    Next
    INDEX
    Explanations

    words related to illustrating or emphasizing ideas and concepts

    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
    enegger
    -0.82
    urat
    -0.74
    kus
    -0.71
    etting
    -0.70
    utic
    -0.68
    cano
    -0.67
    heimer
    -0.67
    astical
    -0.66
    mson
    -0.66
    icio
    -0.66
    POSITIVE LOGITS
     how
    0.90
     why
    0.84
    why
    0.76
     HOW
    0.73
     WHY
    0.72
    how
    0.71
     Hawai
    0.67
     Issues
    0.67
     what
    0.65
     another
    0.64
    Activations Density 0.187%

    No Known Activations