INDEX
Explanations
names starting with the letter "R" followed by a high-ranking sports player or celebrity
names of individuals, particularly those related to sports or public figures
New Auto-Interp
Negative Logits
ADRA
-0.79
ĻĤ
-0.71
REAM
-0.71
EFF
-0.70
disadvant
-0.69
rano
-0.69
RF
-0.67
Percent
-0.67
--------------------------------------------------------
-0.66
FACE
-0.66
POSITIVE LOGITS
theless
0.82
Zac
0.74
restling
0.67
arching
0.67
bender
0.64
umerable
0.64
brethren
0.64
eyes
0.63
heads
0.63
aida
0.62
Activations Density 0.359%