INDEX
Explanations
mentions of low income or financial issues
New Auto-Interp
Negative Logits
ookies
-0.17
ione
-0.16
ute
-0.16
igu
-0.15
aman
-0.15
unk
-0.15
raphics
-0.15
ãĥ³ãĤ¯
-0.15
territory
-0.14
ัà¸ģà¸Ķ
-0.14
POSITIVE LOGITS
enstein
0.25
hanging
0.23
lying
0.23
/no
0.22
country
0.22
lying
0.22
Hanging
0.22
liest
0.21
-cost
0.21
ongan
0.21
Activations Density 0.027%