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. 34
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "one 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
    arius
    -0.65
    avored
    -0.62
    ISC
    -0.62
     clipboard
    -0.61
     interpreter
    -0.59
     administrator
    -0.59
     Forth
    -0.59
     referen
    -0.58
     disadvantage
    -0.57
    desktop
    -0.57
    POSITIVE LOGITS
    uously
    0.71
    )].
    0.65
    ":[{"
    0.64
    ulic
    0.64
     Dynam
    0.64
    ′
    0.64
    "))
    0.63
     Ratings
    0.63
     Square
    0.62
    jection
    0.61
    Activations Density 0.029%

    No Known Activations