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. 214
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "found" in relation to mortality

    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
     laun
    -0.81
     obser
    -0.67
     favor
    -0.66
    anguage
    -0.64
    adan
    -0.62
    edit
    -0.62
    uster
    -0.60
     widest
    -0.60
    aan
    -0.60
     Idea
    -0.59
    POSITIVE LOGITS
    heading
    0.84
    keley
    0.73
    zon
    0.70
    rawdownloadcloneembedreportprint
    0.69
    spir
    0.69
     actionGroup
    0.68
    luaj
    0.68
    footed
    0.67
     dead
    0.66
     hanged
    0.65
    Activations Density 0.018%

    No Known Activations