INDEX
Explanations
phrases that claim something is the best or greatest of all time
New Auto-Interp
Negative Logits
etal
-0.17
esting
-0.16
oba
-0.16
obi
-0.15
htar
-0.15
nonatomic
-0.15
pone
-0.14
ãĥĥãĥĹ
-0.14
EXPECT
-0.14
avin
-0.14
POSITIVE LOGITS
time
0.31
-time
0.27
time
0.27
times
0.21
times
0.20
æĹ¶éĹ´
0.19
.time
0.19
time
0.18
_time
0.17
Time
0.17
Activations Density 0.009%