© 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. 1324
    Prev
    Next
    INDEX
    Explanations

    phrases related to police capabilities and responses in emergency situations

    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
    elin
    -0.75
    inges
    -0.72
    isphere
    -0.64
    DonaldTrump
    -0.63
    rote
    -0.63
    ived
    -0.62
     Empires
    -0.61
    iaries
    -0.61
    ares
    -0.60
     Nightmares
    -0.60
    POSITIVE LOGITS
     intervene
    0.85
     suspend
    0.72
     dismiss
    0.71
     tease
    0.71
     drop
    0.71
     bapt
    0.71
     expel
    0.70
     reprim
    0.70
     exorc
    0.69
     dispatch
    0.69
    Activations Density 0.219%

    No Known Activations