INDEX
Explanations
dates and specific time references
New Auto-Interp
Negative Logits
oat
-0.72
irable
-0.72
opic
-0.69
Reviewer
-0.68
itability
-0.65
culprit
-0.64
older
-0.63
icker
-0.61
obby
-0.60
icket
-0.59
POSITIVE LOGITS
1979
1.21
1953
1.20
1989
1.18
1949
1.17
1993
1.16
1997
1.15
1958
1.15
1988
1.15
1985
1.14
1987
1.14
Activations Density 0.227%