INDEX
Explanations
This neuron activates on mentions of the airway surgery term “tracheostomy” (and related “trache-” stems).
New Auto-Interp
Negative Logits
μέρος
-0.07
PEM
-0.07
Benson
-0.06
byt
-0.06
营业
-0.06
berry
-0.06
ENSOR
-0.06
Quaternion
-0.06
nad
-0.06
slun
-0.06
POSITIVE LOGITS
ze
0.08
rode
0.07
-inch
0.07
de
0.07
ZE
0.07
unker
0.07
leshoot
0.06
führ
0.06
sát
0.06
dese
0.06
Activations Density 0.002%