© 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. 2765
    Prev
    Next
    INDEX
    Explanations

    references to timeframes and frequency of events

    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
    itiz
    -0.63
    itive
    -0.59
    eman
    -0.58
    ibr
    -0.57
     Laden
    -0.56
    ariat
    -0.55
    ens
    -0.55
    intel
    -0.54
    ensitive
    -0.54
    orrow
    -0.54
    POSITIVE LOGITS
     Seconds
    1.07
     seconds
    1.01
     hours
    1.01
     shortest
    1.01
     hour
    0.99
     minutes
    0.96
     days
    0.93
     weeks
    0.90
     hrs
    0.90
     blink
    0.86
    Activations Density 1.037%

    No Known Activations