INDEX
Explanations
The neuron fires on second‐person instructional or directive language, especially occurrences of “You.”
New Auto-Interp
Negative Logits
bumps
-0.07
furry
-0.06
投注
-0.06
_or
-0.06
>>>
-0.06
wit
-0.06
.RunWith
-0.06
�
-0.06
<Card
-0.06
humili
-0.06
POSITIVE LOGITS
promoting
0.06
ischem
0.06
Wallace
0.06
Cert
0.06
AppDelegate
0.06
意
0.06
ुई
0.06
чива
0.06
getActivity
0.06
wav
0.06
Activations Density 0.004%