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. 162
    Prev
    Next
    INDEX
    Explanations

    phrases that express qualifications or caveats in statements

    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
    ouver
    -0.98
    emetery
    -0.79
    rament
    -0.76
    qqa
    -0.73
    foundland
    -0.70
    otonin
    -0.66
    iannopoulos
    -0.66
    icrobial
    -0.66
    entle
    -0.66
    rastructure
    -0.65
    POSITIVE LOGITS
    "},"
    0.79
     thereof
    0.76
    »
    0.70
    but
    0.70
    anded
    0.68
    ��極
    0.64
     preferring
    0.63
    �
    0.63
    especially
    0.61
     BUT
    0.60
    Activations Density 0.276%

    No Known Activations