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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 424
    Prev
    Next
    INDEX
    Explanations

    references to artistic or cultural elements

    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
    DragonMagazine
    -0.73
    orem
    -0.71
     Uni
    -0.70
    opia
    -0.63
    Analysis
    -0.63
     Smile
    -0.63
    abet
    -0.63
    amaru
    -0.62
     Puzzles
    -0.62
    yrinth
    -0.61
    POSITIVE LOGITS
     emanating
    0.79
     abound
    0.78
     ranging
    0.72
     arising
    0.72
     favoring
    0.71
     prolifer
    0.70
     gal
    0.70
    icist
    0.67
    ervative
    0.66
     akin
    0.66
    Activations Density 1.423%

    No Known Activations