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. 117
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically periods

    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
    justice
    -0.87
    opic
    -0.78
    ussia
    -0.77
    ultimate
    -0.76
    uden
    -0.73
    atively
    -0.73
    dayName
    -0.71
    urg
    -0.71
    correct
    -0.71
    jew
    -0.70
    POSITIVE LOGITS
     Tags
    0.89
     Secondly
    0.80
     Funding
    0.80
     Readers
    0.76
     Parameters
    0.76
     Contributions
    0.74
     Cases
    0.73
     Fees
    0.73
     Convers
    0.72
     Advertisement
    0.72
    Activations Density 0.021%

    No Known Activations