INDEX
Explanations
The neuron responds to occurrences of the definite article “the.”
New Auto-Interp
Negative Logits
ownt
-0.07
Language
-0.06
quot
-0.06
indle
-0.06
port
-0.06
enjoys
-0.06
れて
-0.06
HCI
-0.06
lops
-0.06
Baltic
-0.06
POSITIVE LOGITS
The
0.09
.firebaseio
0.07
kaf
0.07
Máy
0.07
glyphicon
0.07
плен
0.07
—
0.06
servlet
0.06
My
0.06
Authorization
0.06
Activations Density 0.020%