INDEX
Explanations
instances of "contact" in a variety of contexts
New Auto-Interp
Head Attr Weights
0:0.01
1:0.02
2:0.07
3:0.34
4:0.01
5:0.03
6:0.05
7:0.12
8:0.07
9:0.05
10:0.07
11:0.10
Negative Logits
生
-1.32
haps
-1.27
yre
-1.26
fif
-1.23
bye
-1.20
edu
-1.17
aughters
-1.15
wat
-1.15
bull
-1.14
RIP
-1.13
POSITIVE LOGITS
kindred
1.18
mosquitoes
1.18
Aether
1.13
mosquit
1.10
surfaces
1.09
SCP
1.09
contacts
1.08
communication
1.06
centres
1.06
sworth
1.05
Activations Density 0.011%