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. 124
    Prev
    Next
    INDEX
    Explanations

    references to the importance of various biological and ecological factors in different contexts

    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
    lead
    -0.79
    田
    -0.73
    contin
    -0.72
    ヴ
    -0.71
    continue
    -0.70
    ultz
    -0.70
    glas
    -0.69
    DEF
    -0.69
    Contin
    -0.68
    poons
    -0.67
    POSITIVE LOGITS
     Polit
    0.67
     Commerce
    0.65
     biology
    0.64
     Secret
    0.62
     Nov
    0.62
     Dinosaur
    0.61
     earliest
    0.61
     earth
    0.61
     infancy
    0.60
     Capitol
    0.59
    Activations Density 0.119%

    No Known Activations