© 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. 2548
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the conjunction "and" in the context of years or time periods

    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
    natureconservancy
    -0.97
    etsk
    -0.69
    ads
    -0.64
    HI
    -0.61
    Us
    -0.61
    ank
    -0.60
    iggle
    -0.59
    hots
    -0.58
    ��
    -0.58
     vulner
    -0.57
    POSITIVE LOGITS
    quel
    0.73
    Introduced
    0.68
     2015
    0.65
     <=
    0.65
    2015
    0.64
    otten
    0.64
     2014
    0.63
     intervening
    0.62
     1962
    0.61
     earlier
    0.61
    Activations Density 0.058%

    No Known Activations