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. 46
    Prev
    Next
    INDEX
    Explanations

    mentions of commercial activities or contexts

    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
    ascript
    -0.78
    oha
    -0.68
    utenberg
    -0.68
    acea
    -0.66
    Tro
    -0.65
     Compl
    -0.64
     Compensation
    -0.64
    ruct
    -0.63
    cffff
    -0.62
    advertisement
    -0.62
    POSITIVE LOGITS
     clos
    0.66
     Hes
    0.64
    izing
    0.63
     ginger
    0.62
     grocer
    0.61
     courts
    0.60
    lihood
    0.60
     FSA
    0.59
     derog
    0.59
    ization
    0.58
    Activations Density 0.043%

    No Known Activations