INDEX
Explanations
King's followed by specific words
New Auto-Interp
Negative Logits
ऊपरी
0.46
ကျ
0.42
kapet
0.41
የተ
0.41
ရှိ
0.40
Დ
0.40
asalamualaikum
0.39
الايه
0.39
kowy
0.38
𖥔
0.38
POSITIVE LOGITS
Speech
0.43
Ransom
0.42
Gambit
0.41
speech
0.40
notice
0.39
Palace
0.39
Speech
0.38
Theatre
0.38
ransom
0.38
Dia
0.37
Activations Density 0.005%