INDEX
Explanations
terms related to the Armenian community and their historical experiences, particularly regarding genocide
New Auto-Interp
Negative Logits
lius
-0.16
acha
-0.16
gaard
-0.15
ãĥ³ãĥĪ
-0.15
ãĤµãĥ¼
-0.15
lenen
-0.15
INES
-0.15
eneg
-0.14
ãĥĵãĥ¼
-0.14
tuk
-0.14
POSITIVE LOGITS
inkel
0.16
heroic
0.15
LOS
0.14
Lyft
0.14
semi
0.14
ilia
0.14
pd
0.14
vill
0.14
Semi
0.14
urm
0.14
Activations Density 0.005%