INDEX
Explanations
mentions of a specific place name, "Srebrenica"
references to a specific location or entity associated with significant historical events
New Auto-Interp
Negative Logits
ongyang
-0.65
handlers
-0.60
bargaining
-0.60
!/
-0.57
privile
-0.57
lda
-0.56
recommendation
-0.54
handler
-0.54
istical
-0.52
Emir
-0.52
POSITIVE LOGITS
shaw
1.40
nen
1.18
sa
1.15
nan
1.07
sis
1.06
cia
1.05
fell
1.01
emies
0.98
s
0.97
thal
0.97
Activations Density 0.059%