INDEX
Explanations
references to academic institutions and their personnel
New Auto-Interp
Negative Logits
brains
-0.17
ilog
-0.16
Dept
-0.15
technical
-0.15
ewe
-0.14
technical
-0.14
Technical
-0.14
arks
-0.14
orks
-0.14
jee
-0.14
POSITIVE LOGITS
Prov
0.38
Prov
0.37
prov
0.36
prov
0.34
chancellor
0.28
Chancellor
0.27
university
0.25
vice
0.25
Vice
0.24
ancellor
0.23
Activations Density 0.147%