© 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
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1361
    Prev
    Next
    INDEX
    Explanations

    instances of the word "race" in various contexts

    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
    ocument
    -0.74
     Unch
    -0.74
    ILLE
    -0.71
     guiActiveUn
    -0.71
    ソ
    -0.69
     Falling
    -0.68
    unch
    -0.66
    EStream
    -0.66
     Friedrich
    -0.62
    venture
    -0.61
    POSITIVE LOGITS
    course
    0.86
    dos
    0.75
    oor
    0.72
     tomatoes
    0.69
     pudding
    0.68
     distance
    0.67
    orio
    0.67
    ONSORED
    0.65
    eed
    0.65
    anas
    0.64
    Activations Density 0.024%

    No Known Activations