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. 199
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation or formatting used to denote separation in text

    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
     blat
    -0.69
     secondly
    -0.69
     hashing
    -0.64
     classify
    -0.63
     proport
    -0.62
    soType
    -0.59
    fact
    -0.58
     Certification
    -0.58
     commissions
    -0.58
     certify
    -0.58
    POSITIVE LOGITS
    Exit
    0.73
    HEAD
    0.67
    ビ
    0.67
    ``
    0.64
     ``
    0.62
    achus
    0.61
    ESE
    0.60
    </
    0.59
    �
    0.59
    coni
    0.59
    Activations Density 0.491%

    No Known Activations