INDEX
Negative Logits
empirically
0.38
influencing
0.36
employed
0.35
provision
0.35
likely
0.35
allocation
0.34
တင်
0.34
GCD
0.34
Self
0.34
веро
0.34
POSITIVE LOGITS
sandpaper
0.62
snakes
0.59
jellyfish
0.59
火山
0.59
mushrooms
0.57
puppies
0.57
reptiles
0.57
sardines
0.57
pudding
0.56
volcano
0.56
Activations Density 0.094%