INDEX
Explanations
phrases related to outdoor activities and social interactions
New Auto-Interp
Negative Logits
cl
-0.17
deer
-0.16
642
-0.15
ime
-0.15
gard
-0.14
foreground
-0.14
ardon
-0.14
isia
-0.14
lá
-0.14
-0.14
POSITIVE LOGITS
yat
0.16
dux
0.16
eof
0.15
бом
0.14
глÑĥ
0.14
ÑģÑĤÑĢов
0.14
ieves
0.14
ngth
0.14
æ°¸
0.14
benh
0.14
Activations Density 0.408%