INDEX
Explanations
mentions of the name "Ann" and context-related references to it
New Auto-Interp
Negative Logits
-0.54
(
-0.50
B
-0.49
Me
-0.49
G
-0.48
key
-0.48
who
-0.47
,
-0.46
For
-0.46
P
-0.45
POSITIVE LOGITS
SequentialGroup
1.05
Announcement
0.96
announcement
0.96
themſelves
0.96
itſelf
0.95
ſelves
0.93
فريبيس
0.91
Announcement
0.91
poffe
0.91
purpoſe
0.90
Activations Density 0.120%