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. 109
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of individuals

    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
    Discover
    -0.85
    Runtime
    -0.80
    Disclaimer
    -0.77
    obar
    -0.77
    Britain
    -0.74
    Journal
    -0.73
    Interstitial
    -0.72
    BOOK
    -0.71
    Featured
    -0.70
    Availability
    -0.69
    POSITIVE LOGITS
     Gross
    0.79
     Pist
    0.78
     Pett
    0.77
     Hed
    0.76
     Harden
    0.74
     Kn
    0.74
     Fle
    0.74
     Rez
    0.74
     Beg
    0.73
     Hull
    0.73
    Activations Density 0.139%

    No Known Activations