INDEX
Explanations
the imperative form of verbs
New Auto-Interp
Head Attr Weights
0:0.08
1:0.07
2:0.06
3:0.08
4:0.09
5:0.09
6:0.07
7:0.09
8:0.09
9:0.08
10:0.07
11:0.07
Negative Logits
discern
-1.99
navigate
-1.97
alike
-1.96
ascript
-1.95
enabled
-1.94
surn
-1.89
therefore
-1.88
wielding
-1.84
prompted
-1.81
intending
-1.80
POSITIVE LOGITS
Metal
2.19
MET
2.04
fertilizer
1.99
Toy
1.93
reb
1.92
Cro
1.91
ł
1.90
peanuts
1.87
Soda
1.84
ycle
1.84
Activations Density 0.000%