INDEX
Explanations
punctuation marks, particularly parentheses and periods
New Auto-Interp
Negative Logits
nodd
-0.75
cabbage
-0.70
kettle
-0.69
therap
-0.67
fashion
-0.67
hacks
-0.64
elling
-0.64
neighb
-0.63
butcher
-0.62
wiser
-0.62
POSITIVE LOGITS
aspx
0.96
wav
0.85
Retrieved
0.84
tif
0.81
mp
0.80
Accessed
0.78
jpg
0.78
*)
0.77
igham
0.76
arget
0.76
Activations Density 0.020%