© 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. 1309
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" indicating conjunctions in the text

    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
    execute
    -0.74
    EStream
    -0.73
    arians
    -0.71
    ftime
    -0.69
    uyomi
    -0.64
    achusetts
    -0.64
    berra
    -0.63
    ality
    -0.63
    alcohol
    -0.62
    ipe
    -0.62
    POSITIVE LOGITS
     hilarious
    0.73
     ludicrous
    0.70
     incredible
    0.69
     shaky
    0.69
     slim
    0.69
     hefty
    0.68
     proverbial
    0.68
     minimal
    0.68
     Rez
    0.67
     glowing
    0.67
    Activations Density 0.234%

    No Known Activations