INDEX
Explanations
references to durations of time and anticipation related to events
New Auto-Interp
Negative Logits
STDOUT
-0.16
hra
-0.14
erece
-0.14
argent
-0.14
lingen
-0.13
illa
-0.13
Dest
-0.13
EMA
-0.13
012
-0.13
ì·¨
-0.13
POSITIVE LOGITS
spent
0.33
spent
0.24
of
0.22
away
0.19
spend
0.18
elapsed
0.18
oyal
0.17
ago
0.16
Spend
0.15
-long
0.15
Activations Density 0.044%