INDEX
Explanations
time-related phrases denoting the passing of time
expressions related to the passage of time
New Auto-Interp
Negative Logits
ãĥĻ
-0.84
ãĥ¤
-0.73
untled
-0.64
bush
-0.61
ãĥ³ãĤ¸
-0.60
Front
-0.59
STA
-0.58
coming
-0.57
liest
-0.57
cham
-0.57
POSITIVE LOGITS
orians
0.82
orian
0.75
elapsed
0.73
ago
0.73
unrem
0.71
since
0.69
ago
0.67
uninterrupted
0.66
peacefully
0.65
ient
0.64
Activations Density 0.107%