INDEX
Explanations
references to the United Nations and its associated agencies or officials
New Auto-Interp
Negative Logits
ilty
-0.17
CLAIM
-0.15
Westbrook
-0.14
ocol
-0.14
Squ
-0.14
squid
-0.14
isch
-0.14
acion
-0.14
oc
-0.13
BLE
-0.13
POSITIVE LOGITS
UN
0.24
Ban
0.23
UN
0.22
Resident
0.22
Secretary
0.21
Env
0.20
UNS
0.19
envoy
0.19
Ban
0.19
SG
0.19
Activations Density 0.029%