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. 215
    Prev
    Next
    INDEX
    Explanations

    references to projects

    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
    selves
    -0.74
     Rout
    -0.69
    purpose
    -0.68
     expedition
    -0.66
    robe
    -0.64
     Project
    -0.61
     homeland
    -0.61
     scholarships
    -0.60
     classmates
    -0.60
     classmate
    -0.60
    POSITIVE LOGITS
    ariat
    0.67
    ‎
    0.64
     spawned
    0.64
    orum
    0.64
    alla
    0.63
    ↑
    0.63
    imen
    0.62
     Kelvin
    0.62
    idity
    0.62
    ylan
    0.62
    Activations Density 0.072%

    No Known Activations