© 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. 3344
    Prev
    Next
    INDEX
    Explanations

    the word "for" and its repeated usage 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
     township
    -0.63
     Fairfax
    -0.58
     averaging
    -0.56
     unavailable
    -0.55
     disag
    -0.55
     imprint
    -0.55
    eele
    -0.54
    NPR
    -0.54
    hani
    -0.54
     ambient
    -0.54
    POSITIVE LOGITS
    ged
    0.81
    */(
    0.79
    got
    0.78
    ked
    0.76
    agers
    0.75
    go
    0.74
    ties
    0.73
    gel
    0.71
    gotten
    0.71
    wards
    0.69
    Activations Density 0.089%

    No Known Activations