© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 957
    Prev
    Next
    INDEX
    Explanations

    mentions of notable individuals in political 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
    alties
    -0.75
    yssey
    -0.67
    gin
    -0.66
    ered
    -0.66
    ographed
    -0.66
     largeDownload
    -0.65
    ering
    -0.65
    ulz
    -0.64
    guns
    -0.64
    ancy
    -0.63
    POSITIVE LOGITS
     president
    1.44
     director
    1.30
     superintendent
    1.27
     chairman
    1.25
     chancellor
    1.24
     Director
    1.24
     CEO
    1.22
     dean
    1.17
     commander
    1.17
     supervisor
    1.16
    Activations Density 0.655%

    No Known Activations