INDEX
Explanations
references to restaurants and bars
New Auto-Interp
Head Attr Weights
0:0.02
1:0.04
2:0.07
3:0.08
4:0.03
5:0.05
6:0.09
7:0.33
8:0.05
9:0.03
10:0.08
11:0.08
Negative Logits
obin
-1.33
explanatory
-1.15
outline
-1.15
ework
-1.09
papers
-1.03
henko
-1.01
spores
-1.01
orney
-1.01
timelines
-1.00
entropy
-1.00
POSITIVE LOGITS
Cafe
1.33
catering
1.33
frequ
1.20
Café
1.17
Cola
1.15
iquette
1.11
Breakfast
1.10
specializing
1.08
icion
1.07
VERTISEMENT
1.07
Activations Density 0.105%