INDEX
Explanations
actions followed by prepositions
New Auto-Interp
Negative Logits
vaste
0.58
Blot
0.55
wobei
0.53
Graphical
0.53
Slight
0.52
Phen
0.51
Cyclic
0.49
Represents
0.49
Secara
0.49
ത്രം
0.48
POSITIVE LOGITS
into
0.99
out
0.89
away
0.80
outta
0.80
onto
0.74
forth
0.74
into
0.69
away
0.66
ingly
0.65
jack
0.65
Activations Density 0.421%