INDEX
Explanations
Abbreviations and Codes
This neuron responds to numeric tokens or multi-digit codes (i.e. strings of digits, such as legal article numbers or reference codes).
New Auto-Interp
Negative Logits
�
-0.07
%{-0.07
doll
-0.06
لمه
-0.06
понять
-0.06
_SIMPLE
-0.06
impuls
-0.06
φων
-0.06
Ix
-0.06
ustain
-0.06
POSITIVE LOGITS
aired
0.08
者的
0.07
wh
0.07
Pillow
0.07
AUSE
0.07
trước
0.06
'#'
0.06
Event
0.06
nek
0.06
Ấn
0.06
Activations Density 0.192%