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. 8-TRES-DC
    5. 133
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "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
    baugh
    -0.85
    tons
    -0.77
    _-
    -0.75
     Occupations
    -0.71
     Alone
    -0.69
    raq
    -0.68
     SOL
    -0.68
    borough
    -0.67
    gow
    -0.66
    ibur
    -0.66
    POSITIVE LOGITS
     nucleus
    0.80
     suggestion
    0.79
    rouse
    0.71
     ink
    0.71
     opposite
    0.69
     prospect
    0.68
     odds
    0.67
     threat
    0.67
     latest
    0.66
     extent
    0.66
    Activations Density 0.037%

    No Known Activations