© 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. 3328
    Prev
    Next
    INDEX
    Explanations

    references to ongoing controversies

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    arus
    -0.73
    ools
    -0.68
     wrinkles
    -0.66
    icago
    -0.65
    li
    -0.65
    ington
    -0.64
    odd
    -0.64
    culus
    -0.63
    riel
    -0.63
    heid
    -0.62
    POSITIVE LOGITS
     surrounding
    0.87
     gripped
    0.80
     motivated
    0.78
     driven
    0.72
     spawned
    0.72
     prompted
    0.69
     disposed
    0.69
     centered
    0.69
     pertaining
    0.68
     leveled
    0.68
    Activations Density 0.081%

    No Known Activations