© 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. 2745
    Prev
    Next
    INDEX
    Explanations

    references to roles and positions of individuals

    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
    icans
    -0.65
    bec
    -0.64
     fastball
    -0.62
     dipped
    -0.62
     cheated
    -0.61
     crossed
    -0.61
    emed
    -0.60
     transformed
    -0.59
     fooled
    -0.58
    itten
    -0.58
    POSITIVE LOGITS
     mastermind
    0.80
    Director
    0.79
    prime
    0.78
     keynote
    0.77
     founder
    0.75
     founding
    0.70
     grandson
    0.70
    director
    0.70
     eldest
    0.70
     youngest
    0.69
    Activations Density 0.061%

    No Known Activations