INDEX
Explanations
forms of the verb "to be."
New Auto-Interp
Negative Logits
/animate
-0.16
Dre
-0.14
ience
-0.14
åĴ²
-0.14
elo
-0.14
illo
-0.14
574
-0.14
ospace
-0.13
igi
-0.13
venir
-0.13
POSITIVE LOGITS
zin
0.16
ainment
0.15
Shopping
0.14
vinc
0.14
cono
0.14
_algo
0.14
illis
0.13
angu
0.13
bottom
0.13
shopping
0.13
Activations Density 0.361%