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. 160
    Prev
    Next
    INDEX
    Explanations

    instances of emotional expression or personal sentiments

    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
    BuyableInstoreAndOnline
    -0.76
     Lap
    -0.64
    cair
    -0.64
     embod
    -0.63
    accompan
    -0.63
    omore
    -0.61
    oaded
    -0.61
    ool
    -0.61
     flashes
    -0.60
    oward
    -0.60
    POSITIVE LOGITS
    nz
    0.70
    lla
    0.70
    llo
    0.66
    vc
    0.63
     refill
    0.63
    pez
    0.63
    Score
    0.63
    viation
    0.62
    vor
    0.62
    llers
    0.61
    Activations Density 0.124%

    No Known Activations