INDEX
Explanations
discussions related to social issues and advocacy
New Auto-Interp
Negative Logits
ysacchar
-0.63
WaitForSeconds
-0.59
manusia
-0.52
hängigkeit
-0.49
appartamento
-0.48
smaak
-0.48
oprot
-0.47
gebou
-0.46
appliquent
-0.46
ganza
-0.46
POSITIVE LOGITS
topics
1.10
issues
0.89
Topics
0.87
topic
0.81
Topics
0.79
matters
0.78
TOPICS
0.75
Issues
0.74
Issues
0.72
topics
0.71
Activations Density 0.205%