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. 611
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation marks in the 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
     eleph
    -0.84
     subur
    -0.77
     pione
    -0.77
     Skydragon
    -0.74
    ategory
    -0.72
    etheless
    -0.70
    vertisement
    -0.69
    �
    -0.66
    �
    -0.66
    NULL_CHAR
    -0.66
    POSITIVE LOGITS
    aced
    0.75
    ̶
    0.70
    代
    0.70
    rer
    0.68
    Method
    0.65
    alion
    0.64
    ワン
    0.64
    ved
    0.63
    ATHER
    0.63
    Jr
    0.62
    Activations Density 0.110%

    No Known Activations