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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     be
    0.80
     четы
    0.69
    w
    0.66
    wl
    0.65
     up
    0.65
     on
    0.64
     ㅅ
    0.63
    បញ្ចប់
    0.63
     to
    0.62
     అ
    0.62
    POSITIVE LOGITS
    AR
    0.68
    의
    0.64
    I
    0.61
    i
    0.59
    8
    0.59
    IT
    0.57
    6
    0.57
    e
    0.57
    AL
    0.56
    ﻤ
    0.54
    Act Density 13.516%

    No Known Activations