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. 288
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Nicola."

    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
    ifiers
    -0.86
    eous
    -0.76
    bour
    -0.73
     jug
    -0.68
    ifier
    -0.64
     seams
    -0.62
    ors
    -0.62
     mund
    -0.59
    rupulous
    -0.59
    urable
    -0.59
    POSITIVE LOGITS
    llan
    0.77
    actly
    0.76
    oche
    0.74
    ensen
    0.72
    kell
    0.72
    uador
    0.70
    keye
    0.69
    chip
    0.68
    TIME
    0.66
    pez
    0.64
    Activations Density 0.040%

    No Known Activations