INDEX
Explanations
phrases related to migration and movement across borders
New Auto-Interp
Negative Logits
reek
-0.17
pany
-0.16
duce
-0.15
plete
-0.15
Strauss
-0.15
015
-0.15
olo
-0.14
eric
-0.14
ieve
-0.14
348
-0.14
POSITIVE LOGITS
being
0.21
being
0.18
having
0.17
Being
0.17
бÑĭÑĤÑĮ
0.16
être
0.16
owaÄĩ
0.16
Being
0.16
commander
0.16
se
0.15
Activations Density 0.025%