INDEX
Explanations
people's professions or job titles with a particular focus on researchers
roles and titles associated with academic and investigative work
New Auto-Interp
Negative Logits
ciating
-0.81
ibaba
-0.78
avers
-0.75
itting
-0.75
itters
-0.75
perm
-0.75
elt
-0.75
undai
-0.73
awks
-0.73
sels
-0.72
POSITIVE LOGITS
extraord
1.08
laureate
1.01
journalist
0.90
novelist
0.88
ographer
0.85
biologist
0.85
educator
0.84
itatively
0.83
physicist
0.80
scientist
0.79
Activations Density 0.131%