INDEX
Explanations
proper nouns and specific terms related to academic and scientific contexts
New Auto-Interp
Negative Logits
UnusedPrivate
-0.81
a
-0.77
o
-0.65
kasarigan
-0.63
liothèque
-0.61
Kariera
-0.61
edale
-0.60
på
-0.60
RequiresApi
-0.59
Gator
-0.59
POSITIVE LOGITS
Erm
1.07
mers
1.03
JAM
1.03
BBM
1.02
DPM
1.00
JIM
1.00
Dm
0.99
HAM
0.98
HEM
0.98
Bm
0.96
Activations Density 1.380%