INDEX
Explanations
expressions of uncertainty or confusion about a situation
New Auto-Interp
Negative Logits
Daß
-0.94
―――――
-0.75
SCSI
-0.75
ſelf
-0.75
ſy
-0.72
Forumite
-0.71
raiſ
-0.71
eſ
-0.70
crdi
-0.69
חיצוניים
-0.68
POSITIVE LOGITS
️
0.71
Idk
0.63
https
0.63
Idk
0.63

0.62
idk
0.62
nullptr
0.61
nullptr
0.59
<eos>
0.58
Covid
0.57
Activations Density 0.080%