Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 308
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "s"

    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
    stad
    -0.79
    ís
    -0.76
    strip
    -0.75
    pend
    -0.74
    utical
    -0.73
    itus
    -0.71
    reth
    -0.69
    ffee
    -0.69
    frey
    -0.69
    iated
    -0.69
    POSITIVE LOGITS
     mist
    0.67
     progression
    0.65
     midst
    0.63
     corrections
    0.61
     goodwill
    0.61
     merciless
    0.61
     tricks
    0.61
     defences
    0.60
     workforce
    0.60
     relentless
    0.60
    Activations Density 0.186%

    No Known Activations