INDEX
Explanations
references to the Labour Party and related political mentions
New Auto-Interp
Negative Logits
estre
-0.14
nop
-0.14
br
-0.14
bob
-0.14
á»±c
-0.14
ester
-0.14
Hass
-0.13
/rfc
-0.13
Sabb
-0.13
b
-0.13
POSITIVE LOGITS
lama
0.15
ocy
0.15
hood
0.14
chemist
0.14
illin
0.14
ëį°ìĿ´íĬ¸
0.14
ARIANT
0.13
.SDK
0.13
AssignableFrom
0.13
anes
0.13
Activations Density 0.004%