INDEX
Explanations
The neuron flags occurrences of the corporate signature “Enron North America Corp.” in the text.
New Auto-Interp
Negative Logits
buquerque
-0.08
lio
-0.07
Maria
-0.07
GameOver
-0.06
line
-0.06
Mary
-0.06
тие
-0.06
ddie
-0.06
Mary
-0.06
ButtonModule
-0.06
POSITIVE LOGITS
'acc
0.07
740
0.06
груп
0.06
import
0.06
.seed
0.06
tossing
0.06
년
0.06
iv
0.06
(cur
0.06
غل
0.06
Activations Density 0.007%