INDEX
Explanations
mentions of the name "Oliver."
mentions of the name "Oliver."
New Auto-Interp
Negative Logits
mble
-0.79
arching
-0.74
ulhu
-0.73
BOOK
-0.72
eanor
-0.72
hz
-0.69
yip
-0.68
planes
-0.68
âĸ¬
-0.68
habi
-0.67
POSITIVE LOGITS
Twist
0.91
sson
0.88
Oliver
0.85
Wend
0.75
nel
0.73
alia
0.72
tein
0.72
son
0.71
Crom
0.71
Klein
0.69
Activations Density 0.017%