INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     as
    -0.14
    s
    -0.11
    as
    -0.10
    	as
    -0.10
     etc
    -0.09
    As
    -0.09
     tästä
    -0.09
     όπως
    -0.09
     be
    -0.09
     cómo
    -0.09
    POSITIVE LOGITS
     follows
    0.17
    ynchronous
    0.16
     opposed
    0.16
    ynchron
    0.16
    cribing
    0.15
    ynchronously
    0.15
     onderdeel
    0.15
     well
    0.15
    cribes
    0.15
    pires
    0.14
    Act Density 0.209%

    No Known Activations