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. 676
    Prev
    Next
    INDEX
    Explanations

    sentences that address various societal issues or topics

    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
     challeng
    -0.74
     arrang
    -0.68
    ��
    -0.65
     continuously
    -0.64
     mathemat
    -0.63
     plent
    -0.62
     quir
    -0.61
     accomp
    -0.59
     nodd
    -0.59
     intervene
    -0.58
    POSITIVE LOGITS
     Table
    0.68
     Events
    0.65
     Catal
    0.62
     Fees
    0.62
     Basics
    0.62
     Source
    0.62
     pic
    0.62
     Shutterstock
    0.61
     Symptoms
    0.60
     Governors
    0.60
    Activations Density 0.501%

    No Known Activations