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. 149
    Prev
    Next
    INDEX
    Explanations

    terms related to biological processes and physiological conditions

    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
    eways
    -0.93
     Rebell
    -0.67
    iencies
    -0.65
    otions
    -0.62
    ements
    -0.61
    itars
    -0.60
     distances
    -0.60
    azines
    -0.60
    natureconservancy
    -0.60
    undo
    -0.59
    POSITIVE LOGITS
    sounding
    0.82
    CAN
    0.65
    HOU
    0.65
    compatible
    0.65
    method
    0.63
    Rated
    0.63
    PAC
    0.63
    FUL
    0.63
    Works
    0.63
    SHARE
    0.62
    Activations Density 3.420%

    No Known Activations