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. 278
    Prev
    Next
    INDEX
    Explanations

    colons and semicolons used to denote structured information or data points

    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
     Trails
    -0.69
     Gret
    -0.66
     Wink
    -0.63
     collateral
    -0.62
     Weld
    -0.62
     Spiel
    -0.61
     Sparkle
    -0.61
     Wine
    -0.61
     ZIP
    -0.58
     CDs
    -0.58
    POSITIVE LOGITS
    connected
    0.85
    main
    0.81
    ahon
    0.81
    absolute
    0.80
    ウス
    0.80
    render
    0.80
    require
    0.79
    mean
    0.78
    username
    0.78
    awed
    0.76
    Activations Density 0.131%

    No Known Activations