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. 205
    Prev
    Next
    INDEX
    Explanations

    components of the word "meeting"

    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
    oric
    -0.62
     elbow
    -0.60
     footh
    -0.60
     amendments
    -0.60
     inspiration
    -0.60
     nonviolent
    -0.60
     convictions
    -0.60
     elements
    -0.60
     momentum
    -0.59
     innovation
    -0.59
    POSITIVE LOGITS
     ABOUT
    1.00
     PROGRAM
    0.96
     NOTICE
    0.94
     SAY
    0.91
     LIST
    0.90
     SEE
    0.90
     THERE
    0.89
     THEIR
    0.89
     SOME
    0.88
     THAT
    0.87
    Activations Density 0.239%

    No Known Activations