INDEX
Explanations
symbols and punctuation, particularly those that may have special significance or appear frequently in the text
New Auto-Interp
Negative Logits
orado
-0.16
ãĥ³ãĥĪ
-0.15
SCII
-0.15
endi
-0.15
ragen
-0.14
Ñħови
-0.14
è͵
-0.14
izr
-0.13
æķ¬
-0.13
Primitive
-0.13
POSITIVE LOGITS
Inc
0.28
inc
0.28
inc
0.26
Inc
0.25
INC
0.24
-inc
0.23
Incorporated
0.22
.inc
0.22
_inc
0.22
INC
0.21
Activations Density 0.008%