INDEX
Explanations
instances of the phrase "to [verb]" indicating intention or desire
New Auto-Interp
Negative Logits
گر
-0.17
449
-0.17
ubishi
-0.14
ваннÑı
-0.14
824
-0.14
ati
-0.14
cars
-0.14
æłı
-0.14
ancing
-0.14
740
-0.14
POSITIVE LOGITS
eka
0.15
necessarily
0.15
ãĤ»ãĥ³
0.15
_DESCRIPTOR
0.15
McCabe
0.14
Barn
0.14
ilst
0.14
åĬ©
0.14
ÙħÙĪØ§Ø·
0.13
iced
0.13
Activations Density 0.021%