INDEX
Explanations
words related to individuals who have graduated from an educational institution
references to alumni and their impact or involvement
New Auto-Interp
Negative Logits
lihood
-0.68
erness
-0.65
plays
-0.65
Simple
-0.62
Nightmares
-0.60
Printed
-0.60
Simulator
-0.60
baby
-0.59
Simple
-0.59
Robot
-0.59
POSITIVE LOGITS
umni
1.14
uates
1.10
alumni
1.05
olor
0.85
uate
0.82
rities
0.82
alum
0.79
Reviewer
0.76
lia
0.74
ulty
0.74
Activations Density 0.020%