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. 605
    Prev
    Next
    INDEX
    Explanations

    the word "just" used in various contexts emphasizing its significance or restriction

    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
    dn
    -0.69
    aves
    -0.68
    SOURCE
    -0.64
    div
    -0.60
    avers
    -0.60
    �
    -0.59
    Div
    -0.59
    ean
    -0.58
    icon
    -0.58
    av
    -0.58
    POSITIVE LOGITS
    hyde
    0.67
    Reviewer
    0.64
     snag
    0.63
     stumble
    0.63
    tackle
    0.62
    idth
    0.60
    psey
    0.60
     foreseeable
    0.60
    kef
    0.60
     Bounce
    0.58
    Activations Density 0.077%

    No Known Activations