INDEX
Explanations
prompting groups or entities
New Auto-Interp
Negative Logits
拃
0.73
その
0.68
persoon
0.66
женер
0.66
quella
0.66
和我
0.65
సంవత్స
0.65
Quelques
0.65
الش
0.65
יד
0.65
POSITIVE LOGITS
peasants
0.94
soldiers
0.91
animals
0.90
entrepreneurs
0.89
artists
0.88
workers
0.88
players
0.86
employees
0.86
farmers
0.86
astronauts
0.84
Activations Density 0.840%