INDEX
Explanations
references to regulated substances and their implications
New Auto-Interp
Head Attr Weights
0:0.02
1:0.02
2:0.08
3:0.11
4:0.02
5:0.03
6:0.07
7:0.26
8:0.06
9:0.05
10:0.05
11:0.18
Negative Logits
yip
-1.55
ceptor
-1.24
wine
-1.24
yang
-1.19
Bengal
-1.16
rolled
-1.14
eeper
-1.14
vice
-1.12
jong
-1.11
gow
-1.10
POSITIVE LOGITS
Orche
1.25
pread
1.22
iberal
1.17
tsun
1.14
Seraph
1.10
systematic
1.09
corrid
1.06
\<
1.06
adas
1.06
sonian
1.06
Activations Density 0.019%