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. 52
    Prev
    Next
    INDEX
    Explanations

    phrases that denote greatness or superiority in a specific 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
    ghazi
    -0.79
    chedel
    -0.77
    sal
    -0.74
    aceous
    -0.72
    pic
    -0.72
    byte
    -0.69
    ument
    -0.69
    chall
    -0.68
     sqor
    -0.67
    xtap
    -0.67
    POSITIVE LOGITS
     professors
    0.71
     suspects
    0.69
     pharmacies
    0.65
     Maid
    0.64
     murderers
    0.64
     anymore
    0.64
     whence
    0.63
     rapists
    0.63
    ioned
    0.61
     Predators
    0.61
    Activations Density 0.018%

    No Known Activations