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. 363
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate exceptions or additional information being presented

    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
     Palest
    -0.69
    975
    -0.62
     !!
    -0.62
    IGHTS
    -0.61
     STATS
    -0.61
    reports
    -0.61
    ~~~~
    -0.61
    Recommended
    -0.59
     Documents
    -0.58
     McKenna
    -0.58
    POSITIVE LOGITS
    ibaba
    0.96
    icho
    0.74
    isco
    0.73
    vation
    0.72
    icans
    0.69
    dayName
    0.69
    oji
    0.68
    icip
    0.67
    inf
    0.67
    anye
    0.66
    Activations Density 0.022%

    No Known Activations