INDEX
    Explanations

    Google's AI and security

    New Auto-Interp
    Negative Logits
     scottish
    0.56
     Scottish
    0.55
     cysteine
    0.49
    Scottish
    0.47
     egypt
    0.44
     Ayrshire
    0.43
     sword
    0.43
     Essex
    0.43
     oyster
    0.43
     ivory
    0.42
    POSITIVE LOGITS
    Google
    2.17
     Google
    2.09
    google
    1.84
     گوگل
    1.82
     google
    1.80
     गूगल
    1.71
    谷歌
    1.70
     Goog
    1.66
     গুগল
    1.62
    GOOGLE
    1.55
    Act Density 0.058%

    No Known Activations