INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    -storage
    -0.07
    022
    -0.07
    451
    -0.07
     Levine
    -0.06
    frame
    -0.06
    appId
    -0.06
     вихов
    -0.06
    .GetOrdinal
    -0.06
     Reyes
    -0.06
    ivalent
    -0.06
    POSITIVE LOGITS
     sneak
    0.14
     sne
    0.10
    .street
    0.08
     sneakers
    0.07
    tel
    0.07
     creep
    0.07
    0.07
     creeping
    0.07
    чук
    0.07
     wander
    0.07
    Act Density 0.005%

    No Known Activations