INDEX
Explanations
news headlines containing the word "JUST."
the repetition of the word "JUST"
New Auto-Interp
Negative Logits
laus
-0.72
runtime
-0.69
href
-0.69
nep
-0.68
ysis
-0.66
lein
-0.66
ktop
-0.65
plugins
-0.65
ickey
-0.64
pperc
-0.64
POSITIVE LOGITS
WATCHED
1.49
ICE
1.03
IFIC
1.00
IFIED
0.92
ICES
0.86
ifications
0.83
ifi
0.80
Continued
0.78
ices
0.78
Pass
0.74
Activations Density 0.005%