© 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. 2858
    Prev
    Next
    INDEX
    Explanations

    titles of books or works that begin with "The."

    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
     emphasizes
    -0.76
     describes
    -0.76
     hereby
    -0.75
    heim
    -0.73
    leans
    -0.72
     concentrating
    -0.69
     notably
    -0.69
     noticing
    -0.68
     emphasizing
    -0.67
     applaud
    -0.66
    POSITIVE LOGITS
     Meaning
    0.89
     Import
    0.75
     Breed
    0.73
     untold
    0.73
     Struggle
    0.72
     Siege
    0.72
     Tooth
    0.69
     Horse
    0.68
     Names
    0.68
     Changing
    0.68
    Activations Density 0.087%

    No Known Activations