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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 272
    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
     obligations
    -0.70
     Lies
    -0.65
     Doctrine
    -0.59
    76561
    -0.59
    ierre
    -0.59
    cyclopedia
    -0.58
     Achievements
    -0.57
     existence
    -0.56
     Directive
    -0.56
    anni
    -0.56
    POSITIVE LOGITS
     verge
    0.74
     fence
    0.68
     brink
    0.67
     helm
    0.67
     mend
    0.64
    ularity
    0.64
     chopping
    0.63
     Verge
    0.61
     sidelines
    0.60
     saddened
    0.59
    Activations Density 0.041%

    No Known Activations