© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 3266
    Prev
    Next
    INDEX
    Explanations

    connections and relationships in political discourse

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    netflix
    -0.84
    ̶
    -0.82
    din
    -0.81
    akening
    -0.76
    uca
    -0.76
    imester
    -0.74
    een
    -0.74
    osaurs
    -0.74
    ason
    -0.73
    osate
    -0.72
    POSITIVE LOGITS
     dialogue
    0.85
     civic
    0.85
     administrative
    0.82
     economic
    0.81
     lifestyles
    0.81
     socioeconomic
    0.80
     diplomatic
    0.78
     educational
    0.78
     culture
    0.78
     attitudes
    0.77
    Activations Density 0.271%

    No Known Activations