© 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. 2258
    Prev
    Next
    INDEX
    Explanations

    instances of time-related events or sequences

    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
    Previous
    -0.84
    SOURCE
    -0.72
     specifics
    -0.71
    itivity
    -0.70
     actionGroup
    -0.65
     firsthand
    -0.64
     presc
    -0.63
    ml
    -0.61
    rament
    -0.61
    XM
    -0.61
    POSITIVE LOGITS
     Keeper
    0.64
     Rus
    0.64
     Kirk
    0.64
    eware
    0.62
     Rasm
    0.59
     scam
    0.59
     lun
    0.58
     McKay
    0.57
     Khan
    0.56
     Tart
    0.54
    Activations Density 0.108%

    No Known Activations