© 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. 3273
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters in the text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    shows
    -0.74
     conced
    -0.71
     detectable
    -0.70
    inav
    -0.67
     conson
    -0.62
    ************
    -0.62
    =-=-=-=-
    -0.62
    itol
    -0.62
     attribution
    -0.61
     foreskin
    -0.61
    POSITIVE LOGITS
    urat
    0.71
    ez
    0.69
    encia
    0.66
    perse
    0.66
     Poe
    0.66
    catentry
    0.64
    eur
    0.62
     Mirage
    0.62
     Ramos
    0.62
     Amsterdam
    0.61
    Activations Density 0.852%

    No Known Activations