INDEX
Explanations
references to the name "Barbara" and variations of the term "Bab," suggesting a focus on individuals associated with that name
bab followed by suffixes
New Auto-Interp
Negative Logits
}}^
-0.50
}}">
-0.44
Ender
-0.43
Unite
-0.42
/>;
-0.42
yit
-0.42
excite
-0.42
/>";
-0.41
<tr>
-0.40
vistar
-0.40
POSITIVE LOGITS
Bab
1.05
Bab
0.94
BAB
0.89
Barber
0.79
Barbara
0.76
bab
0.76
Babylon
0.71
Barb
0.70
BAB
0.69
bab
0.69
Activations Density 0.009%