INDEX
Explanations
No Explanations Found
New Auto-Interp
Negative Logits
<bos>
-0.54
ſtate
-0.50
difp
-0.50
purpoſe
-0.49
preſent
-0.48
fubject
-0.47
ſche
-0.47
PerformLayout
-0.46
diſt
-0.46
OrDefault
-0.44
POSITIVE LOGITS
has
1.24
has
1.09
Has
1.00
Has
0.97
έχει
0.94
have
0.90
HAS
0.86
HAS
0.84
heeft
0.83
had
0.80
Activations Density 0.000%
No Known Activations
This feature has no known activations.