INDEX
Explanations
references to significant political and historical events
New Auto-Interp
Negative Logits
æĪĸèĢħ
-0.18
pecially
-0.17
especialmente
-0.17
æĪĸ
-0.16
оÑģоб
-0.16
hoặc
-0.15
æĪĸ
-0.15
especially
-0.15
å°¤
-0.15
jika
-0.15
POSITIVE LOGITS
followed
0.29
marking
0.29
amidst
0.26
becoming
0.25
ending
0.25
shortly
0.25
preceded
0.24
after
0.24
amid
0.23
paving
0.23
Activations Density 0.366%