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. 189
    Prev
    Next
    INDEX
    Explanations

    terms related to health issues and their societal impacts

    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
    mental
    -0.66
    �
    -0.60
    paces
    -0.60
    oldown
    -0.60
    alyst
    -0.59
    termination
    -0.59
    cision
    -0.58
    olo
    -0.58
    wcs
    -0.57
    wick
    -0.55
    POSITIVE LOGITS
    itar
    0.62
     pronounce
    0.60
     Mish
    0.60
    natureconservancy
    0.59
     Kore
    0.59
     Shang
    0.57
    oret
    0.56
     Shine
    0.54
     Roose
    0.54
     unlaw
    0.53
    Activations Density 0.266%

    No Known Activations