INDEX
Explanations
references to "Cold War" and concepts associated with coldness
New Auto-Interp
Negative Logits
iasi
-0.17
ifold
-0.15
uchen
-0.15
hta
-0.15
uate
-0.15
ual
-0.15
orious
-0.15
ually
-0.14
bows
-0.14
Meer
-0.14
POSITIVE LOGITS
-blood
0.25
cold
0.22
cold
0.20
Cold
0.20
Cold
0.20
blood
0.20
ness
0.19
ossier
0.16
rette
0.16
ÅĻet
0.16
Activations Density 0.011%