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

    Neuronpedia

    INDEX
    Explanations

    expressions related to algorithm performance and evaluation metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -0.61
     IBOutlet
    -0.59
     ویکی‌پدی
    -0.58
     незавершена
    -0.54
    ImageContext
    -0.51
    Personensuche
    -0.51
    ThemeOverlay
    -0.48
     tkinter
    -0.45
    RSpec
    -0.45
     يتيمه
    -0.44
    POSITIVE LOGITS
     improvement
    0.54
     improvements
    0.52
     erzielt
    0.46
     accuracy
    0.43
     mejora
    0.42
     Improvements
    0.42
     erziel
    0.42
     performance
    0.42
     Improvement
    0.42
    excellents
    0.41
    Act Density 1.215%

    No Known Activations