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. 222
    Prev
    Next
    INDEX
    Explanations

    instances of the word "can't" or "cannot" in various contexts

    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
     Gems
    -0.66
     advis
    -0.62
     discretionary
    -0.61
    bane
    -0.61
    arna
    -0.58
    ér
    -0.58
     wise
    -0.56
     valuable
    -0.56
     AE
    -0.55
     snipp
    -0.55
    POSITIVE LOGITS
    BACK
    0.73
    Mind
    0.72
    rawdownloadcloneembedreportprint
    0.70
    LOD
    0.66
    bring
    0.66
    pmwiki
    0.65
    RP
    0.65
    itational
    0.65
     dstg
    0.63
    gdala
    0.63
    Activations Density 0.017%

    No Known Activations