© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2636
    Prev
    Next
    INDEX
    Explanations

    instances of the article "a" and related phrases, highlighting singular contexts or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovies
    -0.74
    】
    -0.73
    lest
    -0.72
    LED
    -0.67
    cd
    -0.65
    \)
    -0.62
     unsurprisingly
    -0.61
    lf
    -0.61
     someday
    -0.61
    ör
    -0.61
    POSITIVE LOGITS
     totality
    0.91
     continuation
    0.87
     continuum
    0.84
     culmination
    0.78
     manifestation
    0.76
     simulac
    0.72
     transitional
    0.71
     rehearsal
    0.71
     sovereign
    0.70
     containment
    0.70
    Activations Density 0.204%

    No Known Activations