INDEX
Explanations
bacteria
The neuron fires for mentions of bacterial infections (e.g. the words “bacterial” and “infections”).
New Auto-Interp
Negative Logits
าถ
-0.07
,column
-0.07
анны
-0.07
hari
-0.07
division
-0.07
nối
-0.07
params
-0.07
tagName
-0.07
strdup
-0.06
lantern
-0.06
POSITIVE LOGITS
yg
0.06
_GEN
0.06
刻
0.06
rá
0.05
0.05
outline
0.05
GENERAL
0.05
개발
0.05
现
0.05
dansk
0.05
Activations Density 0.013%