INDEX
Explanations
the word "company" or phrases related to social interaction and relationships
references to social interactions and companionship
New Auto-Interp
Negative Logits
Nadu
-0.57
mbudsman
-0.56
timelines
-0.55
MAP
-0.55
liam
-0.55
Annotations
-0.53
Infrastructure
-0.52
Department
-0.51
mbuds
-0.50
fixes
-0.50
POSITIVE LOGITS
vre
0.71
arious
0.70
henko
0.67
inence
0.64
ertain
0.62
rious
0.62
pants
0.61
ording
0.59
hest
0.59
ilage
0.59
Activations Density 0.400%