INDEX
Explanations
words related to philosophy and belief systems
New Auto-Interp
Head Attr Weights
0:0.05
1:0.02
2:0.11
3:0.12
4:0.22
5:0.02
6:0.19
7:0.03
8:0.05
9:0.04
10:0.05
11:0.03
Negative Logits
yne
-1.30
describ
-1.23
disg
-1.21
trance
-1.20
<<
-1.19
agine
-1.19
%%
-1.16
vomit
-1.16
&&
-1.14
fashion
-1.13
POSITIVE LOGITS
田
1.50
spring
1.39
裏�
1.36
thereof
1.35
ICAN
1.32
osphere
1.28
Pearson
1.20
mable
1.19
therein
1.19
�
1.18
Activations Density 0.125%