© 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. 945
    Prev
    Next
    INDEX
    Explanations

    variations of the phrase "to a [degree/extent]"

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     indications
    -0.70
     properties
    -0.68
    phrine
    -0.66
     prophe
    -0.65
     newsletters
    -0.65
     predictions
    -0.63
     recordings
    -0.63
     advertisements
    -0.63
     smugglers
    -0.62
     services
    -0.62
    POSITIVE LOGITS
    lot
    0.87
    thora
    0.72
    elta
    0.67
    jury
    0.67
    eg
    0.67
    league
    0.66
    major
    0.66
     degree
    0.66
    brand
    0.66
    majority
    0.65
    Activations Density 0.037%

    No Known Activations