© 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. 3129
    Prev
    Next
    INDEX
    Explanations

    instances of the word "meeting."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Flo
    -0.72
     Jeanne
    -0.70
    soever
    -0.66
     Yog
    -0.66
     Geh
    -0.64
     Elf
    -0.64
    ¯¯
    -0.64
     Eva
    -0.64
     Gren
    -0.63
     Seymour
    -0.63
    POSITIVE LOGITS
    oil
    0.84
    ourcing
    0.78
    TPP
    0.74
    ourced
    0.74
    uca
    0.71
    caps
    0.70
    matter
    0.68
    ín
    0.68
    mining
    0.65
    grain
    0.65
    Activations Density 0.049%

    No Known Activations