INDEX
Explanations
occurrences of the word "asking" and associated phrases in sentences
instances of the word "asking."
New Auto-Interp
Negative Logits
Ĥ¬
-0.77
cutting
-0.68
marine
-0.66
rient
-0.64
Nanto
-0.64
ffen
-0.63
lim
-0.63
Tigers
-0.62
Surv
-0.62
ccording
-0.61
POSITIVE LOGITS
rhet
1.20
probing
1.01
questions
0.98
naires
0.95
erville
0.91
asked
0.88
govtrack
0.83
FontSize
0.83
ioned
0.80
asks
0.79
Activations Density 0.041%