INDEX
Explanations
expressions of personal disappointment in films, particularly regarding character development and plot coherence
New Auto-Interp
Negative Logits
itto
-0.16
posure
-0.16
oval
-0.15
AU
-0.15
åłĤ
-0.15
observe
-0.15
arence
-0.14
é¾
-0.14
lama
-0.13
excel
-0.13
POSITIVE LOGITS
IFORM
0.15
PCODE
0.15
ORTH
0.15
LENG
0.14
.ops
0.14
возв
0.14
queryString
0.14
ëŀµ
0.14
cope
0.14
jerne
0.13
Activations Density 0.565%