INDEX
Explanations
words related to modernity or contemporary topics
New Auto-Interp
Negative Logits
cius
-0.92
kick
-0.81
REDACTED
-0.80
iquid
-0.79
NetMessage
-0.77
staking
-0.72
cific
-0.70
cffffcc
-0.68
rations
-0.67
Recommend
-0.66
POSITIVE LOGITS
ized
1.12
isation
1.12
ization
1.03
izations
0.97
era
0.97
izing
0.97
ity
0.94
Era
0.93
civilization
0.93
ised
0.92
Activations Density 0.572%