INDEX
Explanations
central subject of the text
New Auto-Interp
Negative Logits
این
0.37
utilizing
0.36
andı
0.35
incorporating
0.35
designating
0.34
this
0.34
this
0.33
大家
0.33
demonstrating
0.33
الى
0.32
POSITIVE LOGITS
premise
0.90
conceit
0.67
titular
0.64
theme
0.63
premises
0.63
protagonist
0.63
text
0.62
themes
0.60
текст
0.58
texto
0.56
Activations Density 0.011%