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. 114
    Prev
    Next
    INDEX
    Explanations

    references to U.S. political subjects or entities

    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
     unheard
    -0.77
     Carbuncle
    -0.69
     fold
    -0.69
    xual
    -0.67
    agos
    -0.64
    advant
    -0.61
     sqor
    -0.61
     Ital
    -0.61
     Transcript
    -0.60
    raise
    -0.60
    POSITIVE LOGITS
    scientific
    0.70
    ng
    0.70
    Population
    0.67
    アル
    0.64
     shores
    0.62
     lawmakers
    0.62
     legislators
    0.62
    DN
    0.61
    advertising
    0.61
     circles
    0.60
    Activations Density 0.036%

    No Known Activations