INDEX
Explanations
This neuron detects the demonstrative “This.”
New Auto-Interp
Negative Logits
_pedido
-0.07
;\">
-0.07
Billing
-0.07
इक
-0.06
Enum
-0.06
ид
-0.06
Parcel
-0.06
殿
-0.06
یط
-0.06
_Delete
-0.06
POSITIVE LOGITS
kaç
0.06
sue
0.06
_accel
0.06
holds
0.06
िय
0.06
cousins
0.06
accompanying
0.06
�
0.06
contato
0.06
reported
0.06
Activations Density 0.036%