INDEX
Explanations
descriptive nouns and adjectives
New Auto-Interp
Negative Logits
personne
0.59
Person
0.58
person
0.57
একজন
0.53
شخص
0.52
ಒಬ್ಬ
0.52
Female
0.51
osoba
0.49
personer
0.47
person
0.46
POSITIVE LOGITS
humble
0.63
amiable
0.55
unassuming
0.53
youngster
0.52
shy
0.51
crafty
0.51
valiant
0.51
proud
0.50
polite
0.49
hardy
0.48
Activations Density 0.003%