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. 614
    Prev
    Next
    INDEX
    Explanations

    punctuation characters, particularly 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
    cit
    -0.69
     subp
    -0.66
    etheless
    -0.63
    ��
    -0.63
     holders
    -0.61
    orie
    -0.61
    clerosis
    -0.60
     inaccur
    -0.56
     challeng
    -0.56
    ��極
    -0.55
    POSITIVE LOGITS
     Started
    0.74
     Became
    0.72
     Played
    0.69
     Selected
    0.69
     [+]
    0.69
     FANTASY
    0.66
     Ranked
    0.66
     Finished
    0.65
     Remem
    0.65
     Released
    0.62
    Activations Density 0.168%

    No Known Activations