© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2998
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" as a prominent article

    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
    76561
    -0.74
    �士
    -0.70
    etus
    -0.69
    omore
    -0.69
    omics
    -0.69
    estyles
    -0.69
    ))))
    -0.66
    bryce
    -0.64
    rosso
    -0.64
    nikov
    -0.61
    POSITIVE LOGITS
    advertisement
    0.71
     Infantry
    0.56
     Telegraph
    0.55
     declass
    0.54
     dial
    0.53
     motivating
    0.53
     lack
    0.53
     elite
    0.53
     consec
    0.52
     priority
    0.52
    Activations Density 0.413%

    No Known Activations