INDEX
Explanations
family, parents, and lineage
New Auto-Interp
Negative Logits
tweeted
0.55
user
0.53
online
0.50
Photoshop
0.49
Microsoft
0.49
cyberpunk
0.48
tweets
0.48
0.47
0.46
browser
0.46
POSITIVE LOGITS
родителей
0.65
отца
0.65
Parents
0.63
父母
0.63
родители
0.62
genitori
0.60
parents
0.58
परंपरा
0.58
традиции
0.57
семье
0.57
Activations Density 0.071%