INDEX
Explanations
instances of the word "about" referring to various topics or subjects
New Auto-Interp
Negative Logits
972
-0.16
Mile
-0.15
agon
-0.15
wick
-0.15
stanov
-0.15
hva
-0.14
ilde
-0.14
.ga
-0.14
تا
-0.14
onta
-0.13
POSITIVE LOGITS
//{{0.16
atten
0.15
oir
0.15
IID
0.15
ques
0.14
.getSize
0.14
charges
0.14
821
0.13
hor
0.13
DED
0.13
Activations Density 0.027%