© 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. 3195
    Prev
    Next
    INDEX
    Explanations

    mentions of a university

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    hovah
    -0.83
     pione
    -0.74
    cedented
    -0.73
    IE
    -0.72
    INGTON
    -0.72
    ENG
    -0.68
    iev
    -0.68
    erella
    -0.68
    assium
    -0.67
    uper
    -0.66
    POSITIVE LOGITS
     caf
    0.67
     contexts
    0.65
     silence
    0.64
     cocktails
    0.62
     abundance
    0.62
     occasions
    0.62
     membranes
    0.60
     provocation
    0.59
     chairs
    0.59
    mia
    0.59
    Activations Density 0.086%

    No Known Activations