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. 9-TRES-DC
    5. 609
    Prev
    Next
    INDEX
    Explanations

    numerical values and related measurements

    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
    SourceFile
    -0.78
    width
    -0.68
    gorithm
    -0.68
     clim
    -0.66
    orically
    -0.64
    environment
    -0.63
    METHOD
    -0.63
    Enough
    -0.63
    ilib
    -0.62
    MpServer
    -0.62
    POSITIVE LOGITS
     fax
    0.82
     enrolled
    0.81
     coupons
    0.77
     anonymously
    0.75
     unsigned
    0.75
     emailed
    0.75
     signed
    0.75
    signed
    0.72
     vouchers
    0.72
     gifts
    0.72
    Activations Density 3.379%

    No Known Activations