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. 92
    Prev
    Next
    INDEX
    Explanations

    symbols or punctuation that signify emphasis or emotional weight

    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
    cius
    -0.68
     Percent
    -0.67
     Unsure
    -0.67
    aida
    -0.67
    aniel
    -0.64
    claimer
    -0.63
    inguishable
    -0.63
    bane
    -0.62
    FORE
    -0.61
    pires
    -0.61
    POSITIVE LOGITS
     it
    0.70
     behavi
    0.68
     behav
    0.65
     newsletters
    0.63
    Advertisements
    0.62
     observations
    0.62
     aspirations
    0.62
     feelings
    0.62
     plans
    0.61
     notebooks
    0.61
    Activations Density 0.172%

    No Known Activations