INDEX
Explanations
references to specific authors or notable individuals
New Auto-Interp
Negative Logits
uren
-0.15
ochen
-0.15
ocale
-0.13
Temper
-0.13
Lob
-0.13
grou
-0.13
hil
-0.13
Coalition
-0.13
resident
-0.13
Hil
-0.13
POSITIVE LOGITS
æĢ¥
0.15
Sesso
0.14
_______,
0.14
νοÏį
0.14
alty
0.14
anki
0.14
denom
0.14
OLON
0.13
516
0.13
UGC
0.13
Activations Density 0.026%