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. 9-TRES-DC
    5. 670
    Prev
    Next
    INDEX
    Explanations

    references to internet broadband and surveillance-related topics

    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
    Bear
    -0.66
    resses
    -0.63
     Rapt
    -0.63
    yrinth
    -0.61
    axter
    -0.60
     gears
    -0.59
     Elise
    -0.58
     Dwell
    -0.57
     treasures
    -0.57
    rified
    -0.57
    POSITIVE LOGITS
    et
    0.85
    etime
    0.82
    asma
    0.76
    requency
    0.76
    ETS
    0.75
    ets
    0.75
    mosp
    0.73
    km
    0.73
    eter
    0.72
     kW
    0.72
    Activations Density 1.504%

    No Known Activations