Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 9-TRES-DC
    5. 612
    Prev
    Next
    INDEX
    Explanations

    mentions of countries and their diplomatic relations

    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
     coasts
    -0.70
     Afgh
    -0.65
    kus
    -0.63
    �
    -0.63
    ema
    -0.62
     forces
    -0.60
     Balkans
    -0.59
    zbek
    -0.59
     Euph
    -0.59
    Transform
    -0.57
    POSITIVE LOGITS
    /-
    0.70
    :,
    0.65
    >>
    0.64
     »
    0.64
     alias
    0.63
    FN
    0.62
    tesy
    0.61
     Shutterstock
    0.59
    notation
    0.58
     Tow
    0.58
    Activations Density 0.151%

    No Known Activations