INDEX
Explanations
occurrences of the name "Tobin" and its variations
New Auto-Interp
Negative Logits
ford
-0.18
naire
-0.17
ÑĢÑı
-0.16
åº
-0.16
oci
-0.15
iox
-0.15
isor
-0.14
anth
-0.14
ĥn
-0.14
eli
-0.14
POSITIVE LOGITS
hiba
0.23
ább
0.22
.LENGTH
0.18
acco
0.17
xic
0.17
baru
0.16
.makeText
0.16
plit
0.16
º
0.16
istrovstvÃŃ
0.15
Activations Density 0.033%