© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 750
    Prev
    Next
    INDEX
    Explanations

    recurring titles or names in a specific context, particularly related to "Handsome Guy" and "Absurd JS."

    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
     scanner
    -0.69
     organizer
    -0.66
     accelerator
    -0.65
     office
    -0.64
     religiously
    -0.63
     index
    -0.63
     magn
    -0.62
     exorc
    -0.62
    istically
    -0.62
     embargo
    -0.62
    POSITIVE LOGITS
    furt
    0.84
    BuyableInstoreAndOnline
    0.79
    wild
    0.77
     Clothing
    0.75
     Waste
    0.74
    Virgin
    0.74
    heat
    0.72
    Glass
    0.72
     Struggle
    0.72
    Future
    0.71
    Activations Density 0.277%

    No Known Activations