INDEX
Explanations
inhibitors
The neuron primarily detects occurrences of the term “inhibitor” (often in drug names like ACE inhibitors).
New Auto-Interp
Negative Logits
이유
-0.07
ịp
-0.07
:event
-0.07
okud
-0.06
Auch
-0.06
kube
-0.06
J
-0.06
_erase
-0.06
析
-0.06
Brent
-0.06
POSITIVE LOGITS
ライト
0.07
Alert
0.07
chner
0.07
opposes
0.06
sí
0.06
Micha
0.06
warfare
0.06
unfinished
0.06
Sting
0.06
pai
0.06
Activations Density 0.010%