INDEX
Explanations
occurrences of the word "Ein" and its variations
New Auto-Interp
Negative Logits
ulk
-0.16
aly
-0.16
abil
-0.15
ped
-0.15
омеÑĢ
-0.14
::_
-0.14
dog
-0.14
ks
-0.14
trách
-0.13
á»įt
-0.13
POSITIVE LOGITS
agini
0.16
akter
0.15
irie
0.15
reib
0.14
аков
0.14
angs
0.14
anye
0.14
iros
0.14
onu
0.14
åľ³
0.14
Activations Density 0.010%