INDEX
Explanations
words related to sports and athletes
New Auto-Interp
Negative Logits
Leban
-0.16
strap
-0.15
lernen
-0.15
SystemService
-0.15
عادة
-0.14
uffers
-0.14
áv
-0.14
ruba
-0.13
hsi
-0.13
خة
-0.13
POSITIVE LOGITS
Crop
0.16
pike
0.15
sheer
0.15
gener
0.15
Crop
0.14
tha
0.14
chia
0.13
cvs
0.13
met
0.13
starred
0.13
Activations Density 0.026%