INDEX
Explanations
the word "Burundi" mentioned in the text
the word "burundi" or variations of it
New Auto-Interp
Negative Logits
ãĥīãĥ©ãĤ´ãĥ³
-0.94
Ò
-0.73
======
-0.72
ãĥīãĥ©
-0.69
nect
-0.69
utic
-0.67
kefeller
-0.65
toget
-0.64
fig
-0.64
evict
-0.62
POSITIVE LOGITS
erest
1.08
igan
0.90
efined
0.89
ered
0.88
ecided
0.88
lings
0.87
lich
0.85
erer
0.85
emonium
0.84
ling
0.80
Activations Density 0.029%