© 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. 2263
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" in various contexts

    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
     wherein
    -0.70
    Footnote
    -0.69
    Slot
    -0.69
    arity
    -0.68
    racial
    -0.66
    ItemImage
    -0.64
    allo
    -0.64
    �
    -0.64
     �
    -0.63
    ous
    -0.63
    POSITIVE LOGITS
     prophes
    0.81
    onite
    0.73
    enegger
    0.73
    negie
    0.67
     intrins
    0.65
    PDATE
    0.65
    minster
    0.64
     medals
    0.64
     Dawn
    0.64
     immortality
    0.62
    Activations Density 0.117%

    No Known Activations