© 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. 3277
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and references to personal authorship

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    interstitial
    -0.76
    advertising
    -0.74
    IDER
    -0.74
    esm
    -0.67
    Enlarge
    -0.67
    src
    -0.67
    waves
    -0.66
    hap
    -0.66
    Region
    -0.66
    aturdays
    -0.65
    POSITIVE LOGITS
     notebooks
    0.66
     ransom
    0.65
    ewater
    0.58
    iven
    0.56
    olver
    0.56
     composite
    0.56
     McK
    0.55
     Mystic
    0.54
     outstanding
    0.53
    ulators
    0.53
    Activations Density 0.122%

    No Known Activations