INDEX
Explanations
mentions of researchers and universities
mentions of researchers and their affiliations
New Auto-Interp
Negative Logits
iquette
-0.84
estate
-0.81
store
-0.76
venue
-0.74
comments
-0.74
soType
-0.73
usercontent
-0.73
cess
-0.71
deal
-0.69
compl
-0.69
POSITIVE LOGITS
researchers
1.43
researcher
1.34
scientists
1.23
Researchers
1.20
neuroscience
1.18
scientist
1.16
doctoral
1.16
computational
1.16
Researchers
1.15
Neuroscience
1.15
Activations Density 0.346%