INDEX
Explanations
connections and relationships between people and their experiences
New Auto-Interp
Negative Logits
HideFlags
-0.60
kteří
-0.57
talet
-0.51
WriteLiteral
-0.50
referenties
-0.50
<?
-0.49
Tikang
-0.48
знать
-0.47
testng
-0.47
Saison
-0.46
POSITIVE LOGITS
theirs
2.42
hers
2.39
ours
2.36
yours
2.35
mine
2.19
Ours
1.75
yours
1.73
Mine
1.71
Mine
1.70
MINE
1.70
Activations Density 0.393%