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. 282
    Prev
    Next
    INDEX
    Explanations

    names of actors and their roles in various productions

    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
    eatures
    -0.80
    apons
    -0.80
    achelor
    -0.80
    agram
    -0.79
     confir
    -0.79
    tsky
    -0.79
    quickShipAvailable
    -0.77
    aditional
    -0.76
     agre
    -0.75
    thumbnails
    -0.75
    POSITIVE LOGITS
     Gold
    0.69
     Rage
    0.68
     Luffy
    0.66
     Ess
    0.66
     Ze
    0.66
     Jub
    0.64
     Osama
    0.64
     Electricity
    0.63
     Ronaldo
    0.62
     Rush
    0.62
    Activations Density 0.112%

    No Known Activations