INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     endast
    1.03
    DONT
    0.98
    hype
    0.97
     thats
    0.96
    0.96
     تمامی
    0.95
     shitty
    0.94
     esclusivamente
    0.94
     shit
    0.93
     nigga
    0.93
    POSITIVE LOGITS
     several
    1.22
    Several
    1.21
     yesterday
    1.21
     Yesterday
    1.18
     Several
    1.17
     지난해
    1.16
     गत
    1.14
    several
    1.13
    Incidentally
    1.13
     lately
    1.12
    Act Density 0.776%

    No Known Activations