INDEX
Explanations
references to waterfalls and near-death experiences
New Auto-Interp
Negative Logits
ød
-0.15
плав
-0.14
consect
-0.14
phanumeric
-0.14
Sherman
-0.13
flag
-0.13
anh
-0.13
opher
-0.13
Vill
-0.13
Sheriff
-0.13
POSITIVE LOGITS
falls
0.34
Falls
0.33
falls
0.31
Niagara
0.31
waterfall
0.26
casc
0.26
Casc
0.26
spray
0.24
rap
0.22
cascade
0.22
Activations Density 0.017%