INDEX
Explanations
words related to elephants
mentions of elephants and related concepts, particularly in contexts of conservation and poaching
New Auto-Interp
Negative Logits
lly
-0.80
ndra
-0.78
pring
-0.78
nder
-0.77
nergy
-0.77
HER
-0.76
lying
-0.74
mble
-0.73
ername
-0.73
ccording
-0.72
POSITIVE LOGITS
iasis
1.32
elephants
1.02
elephant
0.99
Haram
0.91
ivory
0.85
calf
0.84
Elephant
0.84
herds
0.84
graveyard
0.82
poaching
0.81
Activations Density 0.040%