© 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. 3090
    Prev
    Next
    INDEX
    Explanations

    phrases that include variations of "any kind of" or "any type of."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    alus
    -0.66
     parap
    -0.65
    undy
    -0.58
     landowners
    -0.55
     excellence
    -0.55
    iens
    -0.55
    ropolitan
    -0.55
     needing
    -0.53
    INO
    -0.53
     reeling
    -0.53
    POSITIVE LOGITS
    luster
    0.75
    Deal
    0.72
     batted
    0.72
    ゼ
    0.72
    bowl
    0.72
     largeDownload
    0.69
    poons
    0.67
    Of
    0.67
    ahime
    0.67
     Of
    0.66
    Activations Density 0.028%

    No Known Activations