INDEX
Explanations
high levels of emotional expression or intensity in language
New Auto-Interp
Negative Logits
ledge
-0.16
modo
-0.15
ader
-0.15
inkle
-0.14
ADER
-0.14
oldt
-0.14
iciel
-0.14
rawler
-0.14
//------------------------------------------------------------------------------↵↵
-0.13
.Companion
-0.13
POSITIVE LOGITS
ekip
0.19
matches
0.16
artner
0.16
match
0.15
disput
0.15
вÑĭÑģÑĤÑĥп
0.15
score
0.14
assi
0.14
matches
0.14
team
0.14
Activations Density 0.072%