INDEX
Explanations
references to crises or disasters
New Auto-Interp
Negative Logits
illery
-0.19
weeney
-0.16
endar
-0.15
/Library
-0.14
assage
-0.14
tres
-0.14
ulary
-0.13
irie
-0.13
ason
-0.13
eft
-0.13
POSITIVE LOGITS
zone
0.28
scenario
0.27
-hit
0.26
zones
0.26
situation
0.26
-str
0.24
worse
0.23
-zone
0.23
engulf
0.23
ous
0.23
Activations Density 0.146%