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. 273
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate ongoing actions or efforts

    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
    ieu
    -0.65
    ruby
    -0.63
    scription
    -0.63
     belief
    -0.62
    ependent
    -0.62
    eteenth
    -0.61
     Frie
    -0.61
     Information
    -0.61
     Perspective
    -0.59
     Barron
    -0.59
    POSITIVE LOGITS
     elevate
    0.88
     obtain
    0.87
     enhance
    0.85
     abolish
    0.85
     broaden
    0.83
     stabilize
    0.83
     strengthen
    0.82
    meet
    0.82
     improve
    0.82
     maximize
    0.81
    Activations Density 0.099%

    No Known Activations