INDEX
Explanations
the word "lot" followed by various contexts in text
New Auto-Interp
Negative Logits
perty
-0.97
acus
-0.93
ando
-0.92
Constructed
-0.92
ansas
-0.91
heid
-0.89
sburgh
-0.86
agate
-0.84
gary
-0.84
atchewan
-0.83
POSITIVE LOGITS
amount
0.97
of
0.86
different
0.85
nicer
0.81
bang
0.81
amounts
0.80
predictable
0.79
interesting
0.78
picture
0.78
needed
0.78
Activations Density 4.277%