© 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. 1593
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of 'taking' or becoming established

    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
    adesh
    -0.78
    merce
    -0.75
    ults
    -0.73
    ================================================================
    -0.73
    reshold
    -0.71
    覚醒
    -0.70
    edom
    -0.70
    ¯
    -0.68
    ateg
    -0.67
     VIDEOS
    -0.67
    POSITIVE LOGITS
     root
    0.85
     shape
    0.84
     precedence
    0.74
     inspiration
    0.69
     Shape
    0.69
     hold
    0.68
     notice
    0.62
     flight
    0.61
     place
    0.61
     Toll
    0.61
    Activations Density 0.038%

    No Known Activations