INDEX
Explanations
instances of the verb "to be" in various forms and contexts
New Auto-Interp
Negative Logits
orian
-0.15
dex
-0.14
aser
-0.14
dr
-0.14
ble
-0.14
avit
-0.14
abel
-0.14
ãĥ§
-0.13
mailer
-0.13
raquo
-0.13
POSITIVE LOGITS
677
0.17
λικ
0.15
416
0.15
stile
0.14
cap
0.14
ÙĪØ¬Ùĩ
0.14
sit
0.14
Miner
0.14
antee
0.14
attles
0.14
Activations Density 0.022%