INDEX
Explanations
phrases related to the concept of time
statements about the state of "time."
New Auto-Interp
Negative Logits
eor
-0.87
rouse
-0.83
00007
-0.81
":["
-0.72
iates
-0.70
ifle
-0.70
ategor
-0.69
ptoms
-0.68
ieves
-0.67
pox
-0.66
POSITIVE LOGITS
hereby
0.93
definitely
0.83
ALWAYS
0.77
certainly
0.77
gonna
0.74
prol
0.74
still
0.73
always
0.73
not
0.72
surely
0.72
Activations Density 0.141%