INDEX
Explanations
verbs related to physical activity or games
instances of the word "playing" in various contexts
New Auto-Interp
Negative Logits
pperc
-0.70
hens
-0.65
arta
-0.63
cill
-0.63
FLAG
-0.62
merce
-0.62
hent
-0.61
Dep
-0.60
IPS
-0.60
mber
-0.60
POSITIVE LOGITS
playing
3.43
Playing
2.63
Playing
2.54
playing
2.39
play
2.02
played
2.00
plays
1.87
PLAY
1.68
play
1.60
played
1.57
Activations Density 0.018%