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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 193
    Prev
    Next
    INDEX
    Explanations

    inquiries about quantities or amounts

    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
    illes
    -0.92
    ahime
    -0.90
    ��
    -0.83
    enhagen
    -0.81
    atches
    -0.77
    ascript
    -0.77
    eties
    -0.77
    isons
    -0.76
    ixtures
    -0.74
    uilt
    -0.73
    POSITIVE LOGITS
     daylight
    0.69
     easier
    0.67
     promoter
    0.65
     exception
    0.65
     stead
    0.63
     longer
    0.62
     hotter
    0.62
     sear
    0.61
    ahead
    0.61
     dignity
    0.61
    Activations Density 0.021%

    No Known Activations