© 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
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1333
    Prev
    Next
    INDEX
    Explanations

    activities related to protest and social movements

    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
    itialized
    -0.79
    aceae
    -0.79
    Present
    -0.77
    cum
    -0.70
    present
    -0.69
    anth
    -0.69
    eous
    -0.67
    heat
    -0.65
     fung
    -0.64
    ankind
    -0.63
    POSITIVE LOGITS
     prisons
    1.03
     roads
    0.99
     embassies
    0.94
     entrances
    0.91
     coasts
    0.90
     jails
    0.89
     streets
    0.88
     stadiums
    0.87
     airports
    0.86
     colleges
    0.86
    Activations Density 1.517%

    No Known Activations