INDEX
Explanations
terms associated with conflict and destruction in a military or metaphorical context
New Auto-Interp
Negative Logits
asso
-0.20
zcze
-0.20
ãĤ«ãĥ«
-0.19
åĽº
-0.16
olid
-0.15
.scalablytyped
-0.15
zyÄĩ
-0.14
uien
-0.14
reation
-0.14
urdy
-0.14
POSITIVE LOGITS
aled
0.14
âĹĦ
0.14
[<
0.14
ContentView
0.14
ease
0.14
[
0.13
Fritz
0.13
l
0.13
unto
0.13
Crawford
0.13
Activations Density 0.174%