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. 89
    Prev
    Next
    INDEX
    Explanations

    codes or identifiers associated with models and specifications

    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
     seiz
    -0.81
    emed
    -0.76
    aid
    -0.71
    ription
    -0.71
    session
    -0.71
    DAY
    -0.71
    esson
    -0.71
    udes
    -0.70
    TPS
    -0.69
    owa
    -0.69
    POSITIVE LOGITS
     Aph
    0.69
     Frequ
    0.63
    ,[
    0.62
     quarrel
    0.61
     turb
    0.61
     Fountain
    0.60
     Collider
    0.59
     Brill
    0.59
     Rebels
    0.58
     oneself
    0.58
    Activations Density 0.106%

    No Known Activations