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. 9-TRES-DC
    5. 615
    Prev
    Next
    INDEX
    Explanations

    mentions of specific political figures, particularly Rand Paul and Ted Cruz

    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
    Wilson
    -0.83
    reau
    -0.83
    gerald
    -0.79
    ikers
    -0.74
    velt
    -0.73
    axter
    -0.73
    steen
    -0.71
    zos
    -0.70
     Canaver
    -0.68
    gencies
    -0.68
    POSITIVE LOGITS
     exha
    0.77
     metic
    0.67
     metab
    0.67
     conclud
    0.65
     unden
    0.63
     looph
    0.62
     appre
    0.62
    YL
    0.61
     cumbers
    0.60
     notor
    0.60
    Activations Density 0.085%

    No Known Activations