INDEX
Explanations
references to a specific name: "Hussein."
references to the name "Hussein" in multiple contexts
New Auto-Interp
Negative Logits
rost
-0.79
ritch
-0.72
lishing
-0.71
ļ
-0.70
urnal
-0.70
oats
-0.70
teen
-0.69
talk
-0.69
racted
-0.67
ishable
-0.67
POSITIVE LOGITS
Hussein
1.15
Suk
0.86
Sr
0.82
bands
0.81
itaire
0.78
Abedin
0.77
ali
0.76
Assad
0.74
Abdul
0.73
sein
0.73
Activations Density 0.015%