© 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. 3178
    Prev
    Next
    INDEX
    Explanations

    instances of the word "throw" 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
    conservancy
    -0.80
    ickr
    -0.71
     marches
    -0.70
     concentration
    -0.69
     Photography
    -0.68
    interstitial
    -0.67
    xit
    -0.66
    ña
    -0.66
    amiya
    -0.66
     rallies
    -0.65
    POSITIVE LOGITS
    dayName
    0.95
    rawling
    0.72
     Orig
    0.71
    ielding
    0.67
    abouts
    0.64
    tain
    0.63
    Bound
    0.62
    uid
    0.62
     AQ
    0.61
    oké
    0.60
    Activations Density 0.075%

    No Known Activations