INDEX
Explanations
references to time duration
New Auto-Interp
Head Attr Weights
0:0.02
1:0.02
2:0.19
3:0.11
4:0.19
5:0.03
6:0.10
7:0.09
8:0.03
9:0.04
10:0.05
11:0.08
Negative Logits
acent
-1.78
robe
-1.78
iologist
-1.68
inence
-1.67
izoph
-1.64
reproduce
-1.57
sample
-1.53
イ
-1.52
rics
-1.51
itors
-1.51
POSITIVE LOGITS
busiest
1.66
culmination
1.54
ASY
1.45
clusively
1.42
intens
1.40
Pwr
1.38
Somers
1.37
forging
1.36
exclusive
1.33
Kal
1.32
Activations Density 0.002%