INDEX
Explanations
terms related to modernity and contemporary concepts
New Auto-Interp
Negative Logits
iot
-0.15
oup
-0.15
oll
-0.15
recent
-0.14
uid
-0.14
older
-0.14
ICI
-0.14
ings
-0.14
own
-0.14
latest
-0.14
POSITIVE LOGITS
-day
0.50
-Day
0.37
ized
0.36
ization
0.33
-era
0.33
izing
0.32
ised
0.29
isation
0.28
ity
0.28
izr
0.27
Activations Density 0.028%