INDEX
Explanations
occurrences of names and significant actions related to individuals and their achievements
New Auto-Interp
Negative Logits
Treat
-0.16
kes
-0.15
er
-0.15
Dealers
-0.15
Chronicle
-0.14
anon
-0.14
ab
-0.14
immortal
-0.14
run
-0.13
ET
-0.13
POSITIVE LOGITS
é¡¿
0.15
iliz
0.14
нод
0.14
igy
0.14
figcaption
0.14
ä¹ĭä¸Ģ
0.14
ãģ£ãģ¡
0.14
æīķ
0.14
æĸ¹åIJij
0.14
fone
0.14
Activations Density 0.372%