© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1419
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the concept of significance or importance

    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
    ulner
    -0.75
    irect
    -0.60
    ς
    -0.60
    uese
    -0.60
    cept
    -0.60
    xious
    -0.59
    DonaldTrump
    -0.59
    lished
    -0.59
    vised
    -0.59
    ermott
    -0.58
    POSITIVE LOGITS
    brow
    0.66
    needed
    0.64
    BuyableInstoreAndOnline
    0.63
     as
    0.62
    kies
    0.62
    so
    0.60
    naire
    0.59
     gathers
    0.58
    inki
    0.58
    ifies
    0.58
    Activations Density 0.022%

    No Known Activations