© 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. 2312
    Prev
    Next
    INDEX
    Explanations

    mentions of countries along with their defining characteristics or statuses

    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
     Pluto
    -0.74
     Mumbai
    -0.68
     Karachi
    -0.66
     Akron
    -0.65
     Thur
    -0.64
     Everest
    -0.64
     Portsmouth
    -0.63
    Interested
    -0.63
     Princeton
    -0.63
     Bangalore
    -0.62
    POSITIVE LOGITS
    zech
    0.76
    ective
    0.76
    romy
    0.74
     cradle
    0.69
    �
    0.69
    venient
    0.67
    ocratic
    0.66
    nant
    0.66
    places
    0.66
     birthplace
    0.66
    Activations Density 0.126%

    No Known Activations