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. 9-TRES-DC
    5. 627
    Prev
    Next
    INDEX
    Explanations

    phrases related to fitting or integration of objects or concepts

    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
    ��
    -0.83
    ibe
    -0.79
    harm
    -0.71
    kee
    -0.70
    osite
    -0.68
    ELL
    -0.67
    early
    -0.65
    arial
    -0.65
    apo
    -0.63
    arn
    -0.62
    POSITIVE LOGITS
     mounts
    0.68
     +/-
    0.66
     buckets
    0.64
     bucket
    0.63
     gn
    0.62
     trenches
    0.62
     mounting
    0.61
     racks
    0.61
    gres
    0.60
    rats
    0.60
    Activations Density 0.285%

    No Known Activations