INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Hadoop
    -0.08
     steaming
    -0.08
     chewy
    -0.08
    akosha
    -0.08
     chipset
    -0.08
    -0.08
     MATRIX
    -0.08
     HP
    -0.07
    يدان
    -0.07
    加载
    -0.07
    POSITIVE LOGITS
     burglary
    0.13
    0.13
     theft
    0.12
     vandal
    0.12
     robbery
    0.11
     burglar
    0.11
     चोरी
    0.11
     Theft
    0.10
     nighttime
    0.10
     violent
    0.10
    Act Density 0.036%

    No Known Activations