INDEX
Explanations
references to geographic regions, specifically the Southern Hemisphere
New Auto-Interp
Negative Logits
ujednoznacz
-0.75
peony
-0.72
Scarecrow
-0.71
Menlo
-0.69
Transformers
-0.66
cocoon
-0.64
Curran
-0.62
elbows
-0.62
ści
-0.62
emlrt
-0.61
POSITIVE LOGITS
Southern
2.17
Southern
2.03
SOUTHERN
1.82
southern
1.77
southern
1.63
Sou
1.14
therners
1.07
Sou
1.00
Sout
0.98
thern
0.97
Activations Density 0.073%