© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 3206
    Prev
    Next
    INDEX
    Explanations

    comparisons related to perceptions and rankings of countries or groups

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     distingu
    -0.81
     defin
    -0.73
     sequ
    -0.72
    natureconservancy
    -0.72
    ��
    -0.71
     trending
    -0.71
     differently
    -0.70
     direction
    -0.70
    scoring
    -0.68
     collide
    -0.68
    POSITIVE LOGITS
     Handling
    0.83
     Rye
    0.77
     Bunker
    0.76
     Ezek
    0.75
     Coconut
    0.74
    irlf
    0.73
     Passage
    0.72
     Reasons
    0.72
     Cay
    0.71
     Witch
    0.71
    Activations Density 0.489%

    No Known Activations