INDEX
Explanations
past participle forms of verbs
New Auto-Interp
Negative Logits
canf
-0.15
lÃŃ
-0.15
766
-0.15
iated
-0.15
rored
-0.14
acted
-0.14
itti
-0.14
vÃŃ
-0.14
åΰäºĨ
-0.14
monds
-0.14
POSITIVE LOGITS
Got
0.31
got
0.30
Got
0.28
GOT
0.27
got
0.25
gotta
0.24
long
0.19
yet
0.17
always
0.17
heard
0.16
Activations Density 0.094%