© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 696
    Prev
    Next
    INDEX
    Explanations

    references to cups of beverages

    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
    elaide
    -0.70
    ii
    -0.70
    isco
    -0.62
     Dame
    -0.62
    ECD
    -0.59
    oday
    -0.58
    lvl
    -0.58
    RFC
    -0.58
    €
    -0.58
    GHz
    -0.57
    POSITIVE LOGITS
    knife
    0.75
    board
    0.72
     noodles
    0.72
    stick
    0.70
     actionGroup
    0.69
    poon
    0.69
    blance
    0.67
    boards
    0.67
     chang
    0.65
    cake
    0.63
    Activations Density 0.099%

    No Known Activations