© 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. 1267
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Wednesday."

    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
    -+
    -0.70
    encia
    -0.69
     mosqu
    -0.66
    ensus
    -0.64
    inant
    -0.58
    gery
    -0.58
    hirt
    -0.58
    escription
    -0.56
     fracture
    -0.56
    ciation
    -0.55
    POSITIVE LOGITS
     night
    0.81
     evening
    0.77
     afternoon
    0.70
     nights
    0.64
     Fahrenheit
    0.63
     morning
    0.63
     evenings
    0.57
    Night
    0.57
     beh
    0.55
    xual
    0.54
    Activations Density 0.054%

    No Known Activations