Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 9-TRES-DC
    5. 607
    Prev
    Next
    INDEX
    Explanations

    the definite article "the" 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
    tein
    -0.66
    ersen
    -0.66
    Flight
    -0.64
    uti
    -0.62
    ancy
    -0.62
    eting
    -0.62
    roots
    -0.61
    angelo
    -0.61
    hawks
    -0.59
    esters
    -0.59
    POSITIVE LOGITS
    azeera
    0.65
     same
    0.64
     restroom
    0.62
     newest
    0.62
     comr
    0.59
     slightest
    0.58
     rab
    0.58
     Fres
    0.57
     pseudonym
    0.56
     fres
    0.56
    Activations Density 0.141%

    No Known Activations