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. 27
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Hay."

    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
     graz
    -0.69
     fries
    -0.63
     Whale
    -0.61
     Seym
    -0.61
     Yose
    -0.60
     Hers
    -0.60
    adelphia
    -0.60
     Mayweather
    -0.60
     Crimean
    -0.60
     Amos
    -0.59
    POSITIVE LOGITS
    ensible
    0.80
    ople
    0.80
    mitted
    0.79
    ato
    0.78
    iva
    0.77
    nt
    0.77
    ival
    0.77
    ials
    0.76
    aldi
    0.76
    iev
    0.75
    Activations Density 0.027%

    No Known Activations