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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1710
    Prev
    Next
    INDEX
    Explanations

    references to political appointments and actions

    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
    linger
    -0.79
     Desire
    -0.75
     Rica
    -0.74
     Manny
    -0.69
     Uri
    -0.66
    enta
    -0.66
    ヴ
    -0.65
     Judah
    -0.65
    assetsadobe
    -0.65
    fried
    -0.65
    POSITIVE LOGITS
     periods
    0.98
     compounds
    0.94
     fronts
    0.92
     groups
    0.92
     predecessors
    0.90
     brushes
    0.90
     churches
    0.90
     clinics
    0.89
     baskets
    0.88
     businesses
    0.87
    Activations Density 0.905%

    No Known Activations