INDEX
Explanations
references to Saddam Hussein and related events
references to Saddam Hussein
New Auto-Interp
Negative Logits
ilver
-0.69
Merit
-0.67
hire
-0.65
DRAG
-0.63
Forest
-0.62
FL
-0.62
Wild
-0.61
RAFT
-0.61
LOAD
-0.60
ritch
-0.59
POSITIVE LOGITS
Hussein
1.60
Saddam
1.13
Mubarak
1.00
Hussain
0.94
achev
0.89
dictator
0.87
iyah
0.78
seiz
0.76
Tayyip
0.72
Assad
0.71
Activations Density 0.006%