INDEX
Explanations
references to skiing and skiing-related activities
New Auto-Interp
Negative Logits
/tos
-0.17
sefer
-0.15
odu
-0.14
Flores
-0.14
_kw
-0.14
tpl
-0.14
Ciudad
-0.14
ileÅŁ
-0.14
vens
-0.13
ôn
-0.13
POSITIVE LOGITS
ski
0.61
Ski
0.56
skiing
0.54
snow
0.50
ski
0.45
SKI
0.44
snow
0.43
Snow
0.43
Snow
0.42
powder
0.38
Activations Density 0.166%