Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to time durations, specifically those mentioning years, weeks, or months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    [Time period] + "ago"

    np_acts-logits-general · gemini-2.0-flash

    time ago

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intptr
    -0.64
    AccessorTable
    -0.64
    AntiForgeryToken
    -0.63
     насељу
    -0.60
     فريبيس
    -0.60
     AssemblyProduct
    -0.60
    urlpatterns
    -0.59
    ponses
    -0.58
    <bos>
    -0.56
    ContentAsync
    -0.56
    POSITIVE LOGITS
     ago
    1.97
    ago
    1.11
     back
    1.05
     geleden
    1.01
     Ago
    1.00
     atrás
    0.97
     назад
    0.93
     ag
    0.90
     AGO
    0.90
    AGO
    0.86
    Act Density 0.086%

    No Known Activations