© 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. 1779
    Prev
    Next
    INDEX
    Explanations

    the term "significantly" indicating statistical importance or notable differences

    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
    ibaba
    -0.79
    anus
    -0.73
    igon
    -0.70
    ���
    -0.68
    anamo
    -0.65
    onential
    -0.62
    Hunt
    -0.61
     unbeliev
    -0.61
    ENTION
    -0.60
    ription
    -0.60
    POSITIVE LOGITS
     louder
    1.13
     brighter
    1.03
     safer
    1.02
     cheaper
    1.00
     easier
    1.00
     harder
    0.99
     healthier
    0.99
     better
    0.98
     worse
    0.95
     fewer
    0.94
    Activations Density 0.044%

    No Known Activations