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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 760
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly those of individuals and locations

    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
     gospel
    -0.73
    cour
    -0.72
    itialized
    -0.69
     Swedish
    -0.68
     christ
    -0.67
    christ
    -0.67
     quarantine
    -0.65
     Ste
    -0.63
    busters
    -0.62
     regist
    -0.62
    POSITIVE LOGITS
    hran
    0.82
    azel
    0.80
    ushi
    0.72
    imaru
    0.71
    usky
    0.70
    rils
    0.69
    iceps
    0.69
    gdala
    0.69
    inth
    0.68
    enhagen
    0.68
    Activations Density 1.974%

    No Known Activations