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. 132
    Prev
    Next
    INDEX
    Explanations

    phrases that express a comparative or descriptive structure involving the word "of."

    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
    azo
    -0.84
    eto
    -0.68
    IED
    -0.66
    ís
    -0.64
    ERN
    -0.64
    iden
    -0.64
    issan
    -0.61
    Sexual
    -0.61
    nor
    -0.60
    osi
    -0.60
    POSITIVE LOGITS
     bloom
    0.67
    henko
    0.65
    ortment
    0.57
    rush
    0.56
    olicy
    0.56
    anza
    0.56
     filled
    0.56
     hectares
    0.56
    asma
    0.55
    cules
    0.55
    Activations Density 0.020%

    No Known Activations