Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 303
    Prev
    Next
    INDEX
    Explanations

    mentions of official statements or reports

    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
    Constructed
    -0.94
    龍喚士
    -0.88
    soType
    -0.86
    Reviewed
    -0.86
    Factor
    -0.83
    Winner
    -0.82
    ◼
    -0.81
    Rated
    -0.78
    Alias
    -0.77
    Owner
    -0.77
    POSITIVE LOGITS
     butterflies
    0.77
     memo
    0.72
     labs
    0.72
     books
    0.69
     monitoring
    0.67
     monkeys
    0.67
     commentary
    0.66
     squirrel
    0.66
     paper
    0.65
     forests
    0.65
    Activations Density 0.085%

    No Known Activations