© 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. 3092
    Prev
    Next
    INDEX
    Explanations

    instances of the word "break" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    SHIP
    -0.68
    attach
    -0.64
    detail
    -0.64
    �
    -0.61
    inous
    -0.61
     Zup
    -0.61
     shenan
    -0.60
    eva
    -0.60
     Helsinki
    -0.60
    present
    -0.60
    POSITIVE LOGITS
     methane
    0.66
     pessim
    0.65
    angan
    0.62
     Surface
    0.60
     junk
    0.58
    ioxide
    0.58
    ithing
    0.58
     coun
    0.58
    isf
    0.58
    ith
    0.58
    Activations Density 0.070%

    No Known Activations