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. 668
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to anniversaries or significant dates

    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
     chaired
    -0.66
     presided
    -0.65
     borne
    -0.60
     accompanied
    -0.59
     skelet
    -0.57
     hosted
    -0.57
     founded
    -0.54
     Tinker
    -0.54
     Liam
    -0.52
     ridden
    -0.52
    POSITIVE LOGITS
     matters
    0.58
    anks
    0.56
    liction
    0.55
    =#
    0.54
     feats
    0.53
    steps
    0.52
    apo
    0.52
    }.
    0.52
    sets
    0.51
    anity
    0.51
    Activations Density 4.262%

    No Known Activations