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. 153
    Prev
    Next
    INDEX
    Explanations

    mentions of the University of California system and its campuses

    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
    obi
    -0.69
    tec
    -0.67
    azon
    -0.66
    Connector
    -0.65
    sol
    -0.65
    pload
    -0.64
    ien
    -0.63
    FORE
    -0.63
    vez
    -0.63
    Intel
    -0.62
    POSITIVE LOGITS
     neighbourhood
    0.65
    lections
    0.64
    –
    0.64
     bruises
    0.64
    ="#
    0.63
     Buk
    0.63
    ILY
    0.63
     campus
    0.61
     Osh
    0.60
     Heb
    0.59
    Activations Density 0.024%

    No Known Activations