INDEX
Explanations
mentions of the name "Andre"
mentions of the name "Andre."
New Auto-Interp
Negative Logits
inct
-0.99
ulhu
-0.79
stakes
-0.75
dfx
-0.75
lishing
-0.73
manship
-0.71
yrinth
-0.71
plain
-0.68
ead
-0.66
ilial
-0.66
POSITIVE LOGITS
tti
1.12
essen
0.86
byss
0.83
Andre
0.82
Paste
0.76
cats
0.75
Gord
0.74
Vu
0.72
Rus
0.72
XIII
0.69
Activations Density 0.013%