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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 476
    Prev
    Next
    INDEX
    Explanations

    references to progression or advancement in steps

    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
    cius
    -0.64
    antha
    -0.62
    ghazi
    -0.60
    ixie
    -0.60
    htaking
    -0.59
    anooga
    -0.58
    icio
    -0.58
    ributed
    -0.57
    ortium
    -0.57
    atively
    -0.57
    POSITIVE LOGITS
     richer
    1.12
     better
    1.10
     healthier
    1.09
     safer
    1.07
     faster
    1.05
     higher
    1.05
     easier
    1.05
     closer
    1.05
     slower
    1.04
     greater
    1.04
    Activations Density 0.622%

    No Known Activations