INDEX
Explanations
requests and expressions of desire or intention
New Auto-Interp
Negative Logits
^(@)
-1.44
myſelf
-1.42
$_"
-1.39
ſelf
-1.38
Efq
-1.37
itſelf
-1.36
Theſe
-1.34
purpoſe
-1.32
ſche
-1.29
BibitemShut
-1.29
POSITIVE LOGITS
want
2.48
Want
2.16
want
2.13
Want
2.09
wants
1.86
wanted
1.72
WANT
1.61
wanting
1.48
WANT
1.35
wants
1.35
Activations Density 0.109%