© 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. 3099
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "an" 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
     Brach
    -0.66
     glim
    -0.64
    β
    -0.61
    verting
    -0.59
    proc
    -0.59
    root
    -0.58
     graz
    -0.57
     Compar
    -0.57
     dozen
    -0.56
    rou
    -0.56
    POSITIVE LOGITS
     attempt
    0.93
     interview
    0.91
    xious
    0.85
    esthes
    0.83
    eur
    0.83
     unmist
    0.82
     unnamed
    0.82
     orderly
    0.81
    onymous
    0.80
     anonymous
    0.80
    Activations Density 0.024%

    No Known Activations