Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 293
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "hold" in various contexts

    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
    olit
    -0.63
    oxin
    -0.62
    ername
    -0.61
    eker
    -0.60
    shield
    -0.58
     flourished
    -0.58
    iddler
    -0.57
    listed
    -0.57
     inbox
    -0.57
    odder
    -0.56
    POSITIVE LOGITS
     ceremonies
    1.08
     ceremony
    1.05
     weddings
    1.04
     sym
    1.03
     events
    1.02
     concerts
    1.01
     celebrations
    0.98
     elections
    0.96
     demonstrations
    0.95
     screenings
    0.95
    Activations Density 1.773%

    No Known Activations