INDEX
Explanations
the word "The" at the beginning of sentences
New Auto-Interp
Negative Logits
Audiodateien
-0.58
Murphy
-0.55
som
-0.54
\
-0.53
ulton
-0.52
Co
-0.52
Jean
-0.51
-0.51
sub
-0.51
Van
-0.49
POSITIVE LOGITS
<td>
1.29
<<<<<<<<<<<<<<
0.90
myſelf
0.88
himſelf
0.87
itſelf
0.86
RegistryLite
0.82
Theſe
0.78
raiſ
0.77
poffe
0.76
themſelves
0.76
Activations Density 0.020%