INDEX
Explanations
phrases that indicate a focus on a specific subject or topic
New Auto-Interp
Negative Logits
Th
-0.58
dokonce
-0.56
Municipality
-0.54
e
-0.54
IATA
-0.54
thio
-0.53
anlam
-0.51
ornith
-0.50
th
-0.50
ffi
-0.50
POSITIVE LOGITS
the
1.07
"])
0.96
"):
0.95
nakalista
0.90
@[+][
0.89
+#+#
0.88
'):
0.86
)";
0.86
)"),
0.85
"""
0.85
Activations Density 0.017%