© 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. 1396
    Prev
    Next
    INDEX
    Explanations

    conversational phrases and quotations

    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
     interrupts
    -0.72
     Carbuncle
    -0.70
     respecting
    -0.69
     needles
    -0.69
     coordinates
    -0.69
     consulted
    -0.69
     construed
    -0.68
     ticks
    -0.68
     CTR
    -0.68
     Phar
    -0.68
    POSITIVE LOGITS
    hang
    1.10
    Yeah
    1.10
    Oh
    1.03
    look
    1.01
    Yo
    0.99
    Hey
    0.99
    shut
    0.99
    gee
    0.99
    catentry
    0.97
    yeah
    0.97
    Activations Density 0.051%

    No Known Activations