INDEX
Explanations
references to extreme weather conditions and their effects
New Auto-Interp
Negative Logits
adio
-0.17
gens
-0.15
snowy
-0.15
winters
-0.15
Injector
-0.15
Hunger
-0.15
snow
-0.15
wrench
-0.14
ieur
-0.14
hle
-0.14
POSITIVE LOGITS
heat
0.32
Heat
0.30
summer
0.27
Heat
0.26
Summer
0.24
heat
0.23
_heat
0.23
overhe
0.22
summer
0.22
hot
0.22
Activations Density 0.110%