© 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. 3065
    Prev
    Next
    INDEX
    Explanations

    instances of the word "thinking."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     intrins
    -0.75
     quotations
    -0.67
     owe
    -0.66
     noticing
    -0.65
    attr
    -0.64
    arine
    -0.62
    indal
    -0.62
     owes
    -0.61
    abol
    -0.61
    opsis
    -0.60
    POSITIVE LOGITS
     aloud
    0.68
     Twice
    0.64
     ABOUT
    0.64
    ggle
    0.63
     twice
    0.63
    about
    0.63
     neigh
    0.62
    cloth
    0.61
     thous
    0.60
    ilty
    0.60
    Activations Density 0.051%

    No Known Activations