INDEX
Explanations
mentions of specific individuals and their relationships or interactions
New Auto-Interp
Negative Logits
волÑı
-0.15
avra
-0.15
iland
-0.14
Interop
-0.14
oire
-0.14
.jetbrains
-0.14
eniable
-0.14
aign
-0.13
lesia
-0.13
erap
-0.13
POSITIVE LOGITS
quits
0.29
"
0.28
'
0.23
“
0.20
a
0.19
\"
0.17
«
0.17
''
0.16
‘
0.16
li
0.16
Activations Density 0.061%