INDEX
Explanations
This neuron responds to mentions of salary or compensation figures (e.g. annual salary).
New Auto-Interp
Negative Logits
machine
-0.07
anal
-0.06
umpy
-0.06
,item
-0.06
marsh
-0.06
.UserName
-0.06
control
-0.06
expand
-0.06
Award
-0.06
colour
-0.06
POSITIVE LOGITS
举
0.07
.echo
0.07
็บ
0.07
진
0.06
Penguin
0.06
waking
0.06
hk
0.06
нул
0.06
stabbed
0.06
تجه
0.06
Activations Density 0.017%