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. 305
    Prev
    Next
    INDEX
    Explanations

    adjectives signaling high status or significance

    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
    auld
    -0.77
     tremend
    -0.73
     afforded
    -0.71
     accomp
    -0.70
    SPONSORED
    -0.70
    helm
    -0.70
    enough
    -0.70
    leans
    -0.69
    etsy
    -0.68
     feature
    -0.67
    POSITIVE LOGITS
     Nit
    0.79
     Cutter
    0.78
     Cyr
    0.78
     Stella
    0.77
     Opp
    0.77
     PHI
    0.76
     Ort
    0.76
     Mit
    0.76
     Ply
    0.76
     STATS
    0.75
    Activations Density 0.187%

    No Known Activations