INDEX
    Explanations

    verbs indicating action or movement

    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.07
    3:0.08
    4:0.08
    5:0.08
    6:0.07
    7:0.08
    8:0.07
    9:0.08
    10:0.09
    11:0.07
    Negative Logits
     jur
    -2.38
     manoeuv
    -2.01
     Vulkan
    -2.00
     releg
    -1.98
     neb
    -1.95
     gloss
    -1.93
     acron
    -1.91
     decl
    -1.91
    pires
    -1.87
     prevail
    -1.84
    POSITIVE LOGITS
    aky
    2.41
    ucket
    2.34
    plet
    2.33
    aditional
    2.27
    akable
    2.26
    orted
    2.26
    uben
    2.25
    atts
    2.24
    ijah
    2.19
    hoe
    2.19
    Act Density 0.000%

    No Known Activations