INDEX
Explanations
mentions of the name "Rex"
mentions of the name "Rex."
New Auto-Interp
Negative Logits
istics
-0.70
heartedly
-0.66
sidel
-0.66
ItemImage
-0.64
glim
-0.63
cold
-0.62
istically
-0.61
ties
-0.61
coupling
-0.59
revolving
-0.59
POSITIVE LOGITS
Tillerson
1.12
sburg
1.12
Shutterstock
0.99
roth
0.85
Rex
0.84
tremend
0.82
edia
0.78
dale
0.77
Rex
0.77
Features
0.77
Activations Density 0.025%