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. 90
    Prev
    Next
    INDEX
    Explanations

    references to family-related events or gatherings

    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
    azo
    -0.66
    yre
    -0.66
     senseless
    -0.64
     dstg
    -0.64
     Flavoring
    -0.62
    akia
    -0.62
     Pyr
    -0.61
     Codec
    -0.60
    due
    -0.60
     MacArthur
    -0.60
    POSITIVE LOGITS
    puted
    0.69
     nonex
    0.66
     answ
    0.62
    ocated
    0.62
    miss
    0.61
    ー�
    0.60
     upgr
    0.60
     bust
    0.58
    most
    0.58
    kept
    0.58
    Activations Density 1.380%

    No Known Activations