INDEX
Explanations
informal references to a group of people
references to the audience or group referred to as "you guys"
New Auto-Interp
Negative Logits
AMS
-0.67
Init
-0.66
entimes
-0.65
UA
-0.64
Usage
-0.63
Var
-0.63
Appears
-0.63
ague
-0.62
Appearance
-0.62
ãĥ¼ãĥĨ
-0.61
POSITIVE LOGITS
yourselves
1.10
yourself
0.81
cale
0.76
Tube
0.74
edient
0.74
venge
0.73
sir
0.71
pez
0.70
ankind
0.67
selves
0.66
Activations Density 0.219%