INDEX
Explanations
mentions of the word "rubber"
references to rubber and related materials or products
New Auto-Interp
Negative Logits
erest
-0.92
arios
-0.88
ulhu
-0.88
rophe
-0.80
alez
-0.76
################
-0.74
orld
-0.72
imate
-0.71
places
-0.70
erent
-0.70
POSITIVE LOGITS
rubber
1.01
ding
0.97
latex
0.97
tubing
0.85
duck
0.83
Rubber
0.81
neck
0.81
ding
0.79
band
0.79
glove
0.79
Activations Density 0.008%