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. 364
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the significance of a point or idea

    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
    achus
    -0.75
    odox
    -0.75
    ellen
    -0.75
    imbabwe
    -0.71
    oute
    -0.70
     mathemat
    -0.70
    ussen
    -0.70
    aeus
    -0.69
    ultz
    -0.69
    yss
    -0.67
    POSITIVE LOGITS
     pecul
    0.76
     distinction
    0.73
     positives
    0.72
    facts
    0.70
     facts
    0.70
    ties
    0.69
     caveats
    0.69
     difference
    0.68
    ness
    0.67
     trophies
    0.65
    Activations Density 0.088%

    No Known Activations