© 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. 3349
    Prev
    Next
    INDEX
    Explanations

    conjunctions, particularly the word "and."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    rade
    -0.71
    ising
    -0.70
    swick
    -0.69
    Elsewhere
    -0.68
    union
    -0.67
    isers
    -0.67
    hatt
    -0.65
    locks
    -0.65
    wra
    -0.64
    utm
    -0.64
    POSITIVE LOGITS
     noticed
    0.82
     wanted
    0.77
     want
    0.74
     learned
    0.74
     frequ
    0.70
     prefer
    0.69
     enjoyed
    0.69
     decided
    0.69
     specialize
    0.68
     appreciate
    0.68
    Activations Density 0.290%

    No Known Activations