INDEX
Explanations
indicators of excitement and emotional engagement
New Auto-Interp
Negative Logits
enough
-0.17
доÑģÑĤаÑĤоÑĩно
-0.16
Enough
-0.15
åĢ«
-0.15
доÑģиÑĤÑĮ
-0.14
доÑģÑĤаÑĤ
-0.14
ì§ķ
-0.14
ismet
-0.14
.pretty
-0.14
åIJ¦
-0.14
POSITIVE LOGITS
than
1.46
than
1.21
THAN
1.11
Than
1.08
Than
1.05
-than
1.02
_than
1.00
než
0.76
niż
0.76
än
0.74
Activations Density 0.578%