INDEX
Explanations
descriptors of emotional impact and sensory experiences
New Auto-Interp
Negative Logits
them
-0.19
eux
-0.17
esi
-0.16
odo
-0.15
remen
-0.14
éal
-0.14
Them
-0.14
ÏĦοÏħÏĤ
-0.14
един
-0.14
utin
-0.14
POSITIVE LOGITS
they
0.28
it
0.22
soever
0.21
we
0.19
они
0.19
оно
0.18
certain
0.18
ly
0.18
he
0.17
THEY
0.16
Activations Density 0.041%