INDEX
Explanations
discussions related to legislation and social justice issues
New Auto-Interp
Negative Logits
adla
-0.15
^{°}-0.14
Unnamed
-0.14
ocop
-0.14
ÙĪØ²
-0.14
Quang
-0.14
pond
-0.14
ifestyles
-0.13
ë¥
-0.13
rug
-0.13
POSITIVE LOGITS
gun
0.22
mask
0.22
Gerr
0.22
ICE
0.19
standardized
0.19
sanctuary
0.18
Sanctuary
0.18
Background
0.18
Kavanaugh
0.18
529
0.18
Activations Density 0.589%