© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 681
    Prev
    Next
    INDEX
    Explanations

    expressions related to steps or levels in a comparative context

    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
    unci
    -0.81
    acus
    -0.71
    enf
    -0.69
    eca
    -0.69
    ixie
    -0.68
    zik
    -0.68
    olis
    -0.67
    ================================================================
    -0.66
    ---------
    -0.66
    jas
    -0.66
    POSITIVE LOGITS
     slower
    1.11
     higher
    1.02
     smarter
    0.98
     weaker
    0.96
     richer
    0.96
     faster
    0.96
     healthier
    0.95
     poorer
    0.94
     lower
    0.93
     lighter
    0.93
    Activations Density 0.149%

    No Known Activations