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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1340
    Prev
    Next
    INDEX
    Explanations

    references to polls or polling-related terminology

    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
     Ballard
    -0.59
     pioneered
    -0.58
     guise
    -0.57
     capitals
    -0.56
     Patton
    -0.55
     moot
    -0.54
    GBT
    -0.54
     Magnet
    -0.54
     Trident
    -0.54
     ambassadors
    -0.54
    POSITIVE LOGITS
    inating
    0.80
    uters
    0.79
    uting
    0.77
     裏�
    0.75
    stery
    0.72
    mot
    0.72
    ination
    0.71
    ractor
    0.70
    utions
    0.70
    ulous
    0.70
    Activations Density 0.011%

    No Known Activations