© 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. 2535
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "been" in various contexts related to updates or events

    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
    always
    -0.78
     infinite
    -0.69
     knots
    -0.64
    igi
    -0.63
    hower
    -0.61
    enta
    -0.61
     //[
    -0.60
    icio
    -0.59
     actionGroup
    -0.59
    ldom
    -0.58
    POSITIVE LOGITS
    roup
    0.72
    udeb
    0.67
     gain
    0.62
    NW
    0.61
    enth
    0.60
    ueller
    0.59
     introdu
    0.59
    ework
    0.58
    Reviewer
    0.58
    uctions
    0.58
    Activations Density 0.059%

    No Known Activations