INDEX
Explanations
the word "only" in various contexts
New Auto-Interp
Negative Logits
589
-0.15
either
-0.15
ká
-0.13
анÑĥ
-0.13
582
-0.13
sWith
-0.13
anders
-0.13
è¡
-0.13
ÛĮÙĩ
-0.13
ually
-0.13
POSITIVE LOGITS
sino
0.28
but
0.25
بÙĦÚ©Ùĩ
0.23
sondern
0.22
but
0.21
ä½Ĩ
0.19
maar
0.19
ãģ§ãģĻãģĮ
0.18
ÅĽcie
0.17
_but
0.16
Activations Density 0.018%