INDEX
Explanations
This neuron detects mentions of U.S. dollar amounts (the word “dollars” or the “$” sign).
New Auto-Interp
Negative Logits
_open
-0.07
etect
-0.07
Κατηγορία
-0.07
ostí
-0.06
it
-0.06
jihad
-0.06
wx
-0.06
ersistence
-0.06
İY
-0.06
Connect
-0.06
POSITIVE LOGITS
-dollar
0.11
dollar
0.11
dollars
0.11
Dollar
0.10
Doll
0.08
Percent
0.08
dime
0.08
Dollars
0.08
doll
0.07
bucks
0.07
Activations Density 0.008%