INDEX
Explanations
references to the "Hunger Games" series and its characters
New Auto-Interp
Negative Logits
Mellon
-0.15
075
-0.14
Norm
-0.14
Baron
-0.14
affen
-0.13
Silicone
-0.13
asco
-0.13
961
-0.13
achte
-0.13
nm
-0.13
POSITIVE LOGITS
Hunger
0.24
districts
0.21
District
0.20
district
0.19
district
0.19
District
0.18
Surv
0.17
survival
0.17
_district
0.16
hunger
0.16
Activations Density 0.049%