INDEX
Explanations
mentions of collaboration and partnership
phrases expressing collaboration and teamwork
New Auto-Interp
Negative Logits
edit
-0.79
pmwiki
-0.73
ãĤ¨ãĥ«
-0.70
dunno
-0.70
anasia
-0.69
Sov
-0.69
isers
-0.69
killer
-0.69
oiler
-0.68
balk
-0.66
POSITIVE LOGITS
our
1.61
Our
1.12
ours
1.11
OUR
1.08
ourselves
1.07
Our
1.01
us
0.98
my
0.95
these
0.90
this
0.88
Activations Density 0.544%