INDEX
Explanations
instances of strong emotional states or situations involving tension
New Auto-Interp
Negative Logits
aight
-0.19
ween
-0.14
ternet
-0.14
åħ
-0.14
kie
-0.14
skirts
-0.13
ideographic
-0.13
ither
-0.13
agnost
-0.13
inspace
-0.13
POSITIVE LOGITS
[
0.15
provisional
0.15
ome
0.14
ffe
0.13
ilst
0.13
Cop
0.13
Principal
0.13
SM
0.13
Squ
0.13
bol
0.13
Activations Density 0.060%