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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1410
    Prev
    Next
    INDEX
    Explanations

    references to the passage of time and duration of processes

    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
    版
    -0.70
     comprom
    -0.66
    vae
    -0.65
     Es
    -0.65
    EGIN
    -0.64
    20439
    -0.63
    abase
    -0.63
    Û
    -0.63
    ENE
    -0.63
    wcs
    -0.61
    POSITIVE LOGITS
    iation
    0.70
    iated
    0.66
    orce
    0.66
    vention
    0.61
    iator
    0.61
    Split
    0.61
    grad
    0.60
     Skydragon
    0.60
    void
    0.60
    aut
    0.59
    Activations Density 0.041%

    No Known Activations