INDEX
Explanations
mentions of the name "Dana" in various contexts
New Auto-Interp
Negative Logits
*/(
-0.92
asking
-0.76
tered
-0.76
inent
-0.75
worldly
-0.71
oppable
-0.70
bably
-0.69
ties
-0.69
GoldMagikarp
-0.68
invari
-0.67
POSITIVE LOGITS
Scully
0.86
iesel
0.83
Brooke
0.82
utical
0.82
Vin
0.73
Bash
0.73
Rouse
0.72
ei
0.72
elson
0.71
Fowler
0.71
Activations Density 0.019%