© 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. 3338
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "for example" indicating explanations or illustrations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    anchester
    -0.64
    VER
    -0.64
     predomin
    -0.64
     recip
    -0.63
    BILITIES
    -0.62
    oslav
    -0.61
    discrimination
    -0.60
     REALLY
    -0.58
    wide
    -0.57
     MUCH
    -0.57
    POSITIVE LOGITS
    )=(
    0.76
    .
    0.72
    rin
    0.71
    ,
    0.68
    ;
    0.64
    soDeliveryDate
    0.63
    foundland
    0.63
    .–
    0.62
     Siberian
    0.62
    aron
    0.62
    Activations Density 0.046%

    No Known Activations