INDEX
Explanations
terms related to intensifying or worsening situations
New Auto-Interp
Negative Logits
anka
-0.15
象
-0.15
ÄĽj
-0.15
SWG
-0.15
ÄĽn
-0.14
Desc
-0.14
Hans
-0.14
errat
-0.14
.energy
-0.14
hood
-0.13
POSITIVE LOGITS
alten
0.15
Rubin
0.14
ith
0.14
effort
0.14
mlin
0.14
arith
0.13
conds
0.13
/de
0.13
Mitar
0.13
glas
0.13
Activations Density 0.241%