© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1239
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals with initial 'E' in their names

    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
     IMAGES
    -0.66
     pharmacies
    -0.60
     MUCH
    -0.57
     Vampire
    -0.57
     AVG
    -0.56
     Phoenix
    -0.56
     mosques
    -0.56
     pandemonium
    -0.55
    Buyable
    -0.54
     Sof
    -0.54
    POSITIVE LOGITS
    chev
    1.00
    riks
    0.93
    nerg
    0.92
    ner
    0.89
    rs
    0.86
    wart
    0.86
    amon
    0.84
    ctor
    0.84
    rection
    0.84
    ids
    0.82
    Activations Density 0.021%

    No Known Activations