© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1325
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "today" and its variations

    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
    kamp
    -0.78
     Develop
    -0.71
    hops
    -0.70
    eries
    -0.67
    eners
    -0.66
    stals
    -0.64
    OW
    -0.63
     delaying
    -0.62
    覚醒
    -0.62
     Related
    -0.60
    POSITIVE LOGITS
    verages
    0.72
    umption
    0.69
    eret
    0.68
    uably
    0.66
    plet
    0.64
    ugu
    0.63
     ordinary
    0.63
    uga
    0.62
    most
    0.62
     imitation
    0.62
    Activations Density 0.023%

    No Known Activations