© 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. 3269
    Prev
    Next
    INDEX
    Explanations

    determiner "a" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    buquerque
    -0.74
    amac
    -0.68
     Logged
    -0.67
     Ichigo
    -0.64
    adjusted
    -0.62
     Atkins
    -0.62
    assisted
    -0.61
    oresc
    -0.61
    ä
    -0.59
    azel
    -0.59
    POSITIVE LOGITS
     knack
    0.86
     fascinating
    0.73
    hem
    0.72
     shorter
    0.71
     noteworthy
    0.71
     distinct
    0.68
     fascination
    0.68
    eon
    0.67
     tougher
    0.66
     degree
    0.66
    Activations Density 0.098%

    No Known Activations