INDEX
Explanations
expressions of hypocrisy in social and political discourse
New Auto-Interp
Negative Logits
iller
-0.19
ucci
-0.17
AppComponent
-0.16
):?>↵
-0.16
alar
-0.15
ALAR
-0.14
sko
-0.14
integration
-0.14
alic
-0.13
OutOfBoundsException
-0.13
POSITIVE LOGITS
uru
0.16
lately
0.14
im
0.14
ä¹ĭä¸Ģ
0.14
-negative
0.14
RU
0.13
/lists
0.13
oh
0.13
Äĩ
0.13
å·
0.13
Activations Density 0.466%