© 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. 1931
    Prev
    Next
    INDEX
    Explanations

    references to significant locations or geopolitical entities

    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
     Plex
    -0.66
     Synd
    -0.62
     switching
    -0.61
     airing
    -0.60
     defe
    -0.60
     reapp
    -0.60
     ACE
    -0.60
     Emergency
    -0.60
     conditioning
    -0.59
     Soy
    -0.59
    POSITIVE LOGITS
    chwitz
    0.79
    udo
    0.77
    angled
    0.75
    gallery
    0.75
    Jew
    0.74
     Pieces
    0.73
    arl
    0.69
    quote
    0.68
    pieces
    0.68
    angles
    0.68
    Activations Density 2.095%

    No Known Activations