INDEX
Explanations
concepts related to communication and cultural understanding
New Auto-Interp
Negative Logits
mistr
-0.20
Trust
-0.20
Trust
-0.19
distr
-0.19
trusts
-0.19
trust
-0.18
trusting
-0.17
distrust
-0.17
ekl
-0.16
inee
-0.16
POSITIVE LOGITS
Communication
0.30
communication
0.28
Communication
0.27
communic
0.25
communication
0.23
Media
0.22
Audience
0.22
communications
0.21
rhet
0.21
pragma
0.21
Activations Density 0.091%