© 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. 3314
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize duration or length of time

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ワン
    -0.66
    フォ
    -0.66
     pitfalls
    -0.64
     corridors
    -0.61
    otin
    -0.59
    amaz
    -0.59
    artifacts
    -0.59
    MpServer
    -0.57
     Debor
    -0.57
     artif
    -0.56
    POSITIVE LOGITS
    uld
    0.77
    inery
    0.69
     while
    0.68
    inness
    0.63
     lifetime
    0.61
    UTH
    0.60
     reason
    0.59
    unts
    0.58
    irst
    0.58
    ineries
    0.57
    Activations Density 0.077%

    No Known Activations