INDEX
Explanations
dates and numerical data relevant to historical events or figures
New Auto-Interp
Negative Logits
ohan
-0.15
oir
-0.15
uliar
-0.14
avel
-0.14
roje
-0.14
uteur
-0.14
ograms
-0.14
оÑģÑĢед
-0.13
aura
-0.13
ira
-0.13
POSITIVE LOGITS
omi
0.15
ÏĦÏģι
0.15
erb
0.14
yap
0.14
marsh
0.14
ActionCode
0.14
_WP
0.13
forefront
0.13
ido
0.13
Gast
0.12
Activations Density 0.045%