© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1448
    Prev
    Next
    INDEX
    Explanations

    instances of the concept of "thinking" in various contexts

    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
     largeDownload
    -0.67
     Syndrome
    -0.64
     ILCS
    -0.64
    cia
    -0.62
    isy
    -0.62
    oulos
    -0.61
     Observatory
    -0.61
    20439
    -0.60
    iasm
    -0.60
    bourg
    -0.60
    POSITIVE LOGITS
     outside
    0.94
     twice
    0.94
    outside
    0.85
     ahead
    0.81
     beyond
    0.76
    Outside
    0.76
     Outside
    0.74
     outdoors
    0.70
    覚醒
    0.68
     Twice
    0.64
    Activations Density 0.065%

    No Known Activations