© 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. 968
    Prev
    Next
    INDEX
    Explanations

    instances of the word "watched" and its variations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    itives
    -0.72
    abouts
    -0.67
    illery
    -0.66
    imei
    -0.65
    onte
    -0.65
     concess
    -0.65
    achy
    -0.63
    initely
    -0.62
    aches
    -0.61
    assadors
    -0.60
    POSITIVE LOGITS
     Belt
    0.72
     wom
    0.66
     television
    0.65
     TV
    0.65
     Getty
    0.62
    ize
    0.61
     AFP
    0.61
     Newsp
    0.59
     textbooks
    0.59
     Paste
    0.58
    Activations Density 0.028%

    No Known Activations