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. 44
    Prev
    Next
    INDEX
    Explanations

    phrases that describe conditions or scenarios involving the word "when."

    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
    DragonMagazine
    -0.80
    icles
    -0.72
    nces
    -0.71
    videos
    -0.69
    YR
    -0.67
    redd
    -0.66
    ame
    -0.66
    NK
    -0.65
    HK
    -0.63
    AZ
    -0.63
    POSITIVE LOGITS
    gee
    0.68
     influential
    0.60
     emer
    0.59
     attackers
    0.58
     heterogeneity
    0.56
     promoters
    0.56
     your
    0.56
    hello
    0.56
     you
    0.56
     incremental
    0.54
    Activations Density 0.142%

    No Known Activations