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. 177
    Prev
    Next
    INDEX
    Explanations

    specific cultural or regional foods and dishes

    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
    tenance
    -0.78
    reprene
    -0.68
    mortem
    -0.62
    spring
    -0.58
    デ
    -0.57
    rection
    -0.57
    ground
    -0.57
    spection
    -0.55
    lier
    -0.55
    rers
    -0.55
    POSITIVE LOGITS
    yah
    0.70
    externalActionCode
    0.64
     Medals
    0.62
     nep
    0.60
     incent
    0.59
     <+
    0.56
    NI
    0.56
    attribute
    0.55
     looted
    0.55
     unbeliev
    0.54
    Activations Density 0.538%

    No Known Activations