INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Copa
    -0.10
    Comparator
    -0.08
    apit
    -0.08
    jug
    -0.08
    าป
    -0.07
    perf
    -0.07
    כר
    -0.07
     counselling
    -0.07
    来说
    -0.07
     явля
    -0.07
    POSITIVE LOGITS
     Syndrome
    0.08
    _sz
    0.08
    Sz
    0.08
     synd
    0.08
    sz
    0.08
     fallout
    0.08
     syndrome
    0.08
    0.08
    SZ
    0.07
     SZ
    0.07
    Act Density 0.136%

    No Known Activations