INDEX
Explanations
references to seniors or seniority in various contexts
senior roles and titles
New Auto-Interp
Negative Logits
mixtures
-0.41
spilled
-0.41
chas
-0.38
wäh
-0.38
AxisAlignment
-0.38
tomia
-0.37
Hanks
-0.37
merkung
-0.37
habis
-0.36
them
-0.36
POSITIVE LOGITS
Senior
1.68
Senior
1.67
senior
1.66
SENIOR
1.59
senior
1.54
SENIOR
1.45
Seniors
1.37
seniors
1.36
Seniors
1.26
junior
1.06
Activations Density 0.006%