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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     satis
    1.73
     trasport
    1.63
    𝐨
    1.60
    ی
    1.59
    𝐚
    1.56
     darse
    1.54
     adicional
    1.47
    .$,
    1.41
     segura
    1.41
    തിരെ
    1.41
    POSITIVE LOGITS
    к
    1.57
     glimpses
    1.56
    त
    1.50
    ა
    1.45
    ти
    1.43
    ות
    1.40
    ле
    1.34
    ன்
    1.34
    ین
    1.34
    ка
    1.32
    Act Density 0.116%

    No Known Activations