INDEX
Explanations
Support for charities
The neuron fires on words indicating activism, advocacy, or philanthropic/social justice work.
New Auto-Interp
Negative Logits
nth
-0.07
_DIRECT
-0.07
Scripture
-0.06
.x
-0.06
Directive
-0.06
.linear
-0.06
|-
-0.06
Janeiro
-0.06
rupted
-0.06
constraint
-0.06
POSITIVE LOGITS
showModal
0.07
loadChildren
0.06
ADDR
0.06
Palin
0.06
AutoSize
0.06
qua
0.06
Popup
0.06
odial
0.06
ramen
0.06
níci
0.06
Activations Density 0.024%