INDEX
Explanations
expressions of gratitude and support
New Auto-Interp
Negative Logits
:↵↵
-0.15
]:↵↵
-0.15
Fucking
-0.15
à¥įवप
-0.14
DERP
-0.14
.pretty
-0.14
[â̦]↵↵
-0.14
:↵↵
-0.14
FUCK
-0.14
Fuck
-0.13
POSITIVE LOGITS
indeed
0.23
Indeed
0.18
Indeed
0.18
inde
0.17
elder
0.15
agree
0.15
appreciate
0.15
glad
0.15
definitely
0.15
yours
0.14
Activations Density 0.117%