INDEX
Negative Logits
Bald
0.43
putable
0.38
Moses
0.37
iPhone
0.36
ラブ
0.36
poem
0.35
rem
0.35
Scottish
0.35
movies
0.34
Emma
0.34
POSITIVE LOGITS
تل
0.47
Hist
0.46
распро
0.44
Electro
0.44
Hydro
0.43
Hull
0.43
tela
0.42
Amplitude
0.42
ELECTRO
0.42
Resistance
0.41
Activations Density 0.002%