© 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. 3093
    Prev
    Next
    INDEX
    Explanations

    the word "as" used to compare or provide context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    pring
    -0.74
     Nanto
    -0.64
    IDENT
    -0.62
    XM
    -0.62
    ESSION
    -0.61
     nost
    -0.61
    ACTED
    -0.61
    MD
    -0.60
    FN
    -0.60
    BuyableInstoreAndOnline
    -0.58
    POSITIVE LOGITS
    well
    0.76
    cised
    0.68
     Browse
    0.67
    iners
    0.67
    oaded
    0.65
    Writer
    0.65
     cheap
    0.65
     donors
    0.64
    quished
    0.64
     judged
    0.62
    Activations Density 0.059%

    No Known Activations