© 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. 3294
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the letters "ur" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    roma
    -0.74
     anthropology
    -0.67
    heres
    -0.67
    category
    -0.64
     males
    -0.64
    building
    -0.63
     genders
    -0.63
    ndra
    -0.62
    sword
    -0.61
     Communism
    -0.61
    POSITIVE LOGITS
     oun
    0.83
    igree
    0.80
    iband
    0.72
     gladly
    0.69
    aucuses
    0.66
     teasp
    0.66
    ertodd
    0.66
    WARE
    0.66
    ricane
    0.65
    acket
    0.65
    Activations Density 0.031%

    No Known Activations