INDEX
Explanations
references to children and their interactions in various contexts
New Auto-Interp
Negative Logits
asts
-0.73
nologies
-0.69
Rais
-0.67
hares
-0.67
Ziegler
-0.67
isations
-0.67
Councillor
-0.66
rsiniz
-0.65
ising
-0.65
vold
-0.65
POSITIVE LOGITS
kids
1.27
guys
1.24
guy
1.17
guys
1.12
stuff
1.10
GUYS
1.07
kids
1.06
Guys
1.00
kid
0.99
Guys
0.96
Activations Density 0.350%