INDEX
Explanations
This neuron detects mentions of gum disease (references to “gum” together with “disease”).
New Auto-Interp
Negative Logits
onica
-0.06
(coeff
-0.06
766
-0.06
ह
-0.06
Car
-0.06
亚洲
-0.06
------+------+
-0.06
-th
-0.06
ΙΔ
-0.06
ávky
-0.06
POSITIVE LOGITS
pressing
0.08
_EOL
0.07
cum
0.07
stages
0.07
Integer
0.07
par
0.06
-win
0.06
private
0.06
framing
0.06
bị
0.06
Activations Density 0.003%