© 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. 1213
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and social interactions

    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
     dstg
    -0.76
    essors
    -0.70
     upfront
    -0.65
    iHUD
    -0.63
     accompanies
    -0.63
    rontal
    -0.62
    ],"
    -0.62
     breaking
    -0.62
    rawdownloadcloneembedreportprint
    -0.62
    EngineDebug
    -0.59
    POSITIVE LOGITS
    isman
    0.77
    ocry
    0.73
    ィ
    0.71
    abus
    0.67
    can
    0.66
    ESE
    0.64
    rians
    0.62
    acs
    0.61
    ilet
    0.61
     deserve
    0.61
    Activations Density 0.094%

    No Known Activations