© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 498
    Prev
    Next
    INDEX
    Explanations

    elements related to the Pac-12 conference

    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
    hold
    -0.83
    2018
    -0.77
    ammy
    -0.75
     Clicker
    -0.74
    learn
    -0.72
    apo
    -0.72
    joy
    -0.70
    alert
    -0.69
    fair
    -0.67
    ync
    -0.67
    POSITIVE LOGITS
    DN
    0.75
    IONS
    0.69
     declarations
    0.67
    IER
    0.66
    Gs
    0.65
     legends
    0.65
     philosophies
    0.65
    TD
    0.65
     pieces
    0.65
     bodies
    0.64
    Activations Density 0.033%

    No Known Activations