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. 632
    Prev
    Next
    INDEX
    Explanations

    references to food and cooking ingredients

    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
    ample
    -0.72
     Supplementary
    -0.66
     gib
    -0.64
     Catalog
    -0.64
     compartment
    -0.64
     Pricing
    -0.63
    tarians
    -0.62
    monkey
    -0.60
     Frequency
    -0.59
     framed
    -0.59
    POSITIVE LOGITS
    baugh
    0.76
    iversary
    0.73
    usp
    0.72
    pas
    0.71
    ofi
    0.68
    udos
    0.66
    oves
    0.65
    clusively
    0.64
    AIDS
    0.63
    ures
    0.63
    Activations Density 1.582%

    No Known Activations