© 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. 2516
    Prev
    Next
    INDEX
    Explanations

    references to various capital cities

    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
    hiba
    -0.80
     IPM
    -0.71
    zek
    -0.71
    sylv
    -0.70
     fire
    -0.70
    monary
    -0.69
     blaze
    -0.68
    thur
    -0.66
    lynn
    -0.65
    onite
    -0.63
    POSITIVE LOGITS
    arsity
    0.93
    RAFT
    0.79
     Sochi
    0.76
    tech
    0.75
     Kuala
    0.72
     Cannes
    0.70
     downtown
    0.70
     Bangalore
    0.68
    PHOTOS
    0.65
     �
    0.64
    Activations Density 0.085%

    No Known Activations