INDEX
Explanations
references to blogs or blogging content
New Auto-Interp
Negative Logits
Waterford
-0.54
Kind
-0.52
hami
-0.51
Somers
-0.51
NIS
-0.50
Kind
-0.50
När
-0.50
huawei
-0.49
Rptr
-0.48
Requirement
-0.48
POSITIVE LOGITS
BLOG
1.10
Blog
1.05
Blog
1.04
blog
1.02
blog
1.00
BLOG
0.98
Blogs
0.98
Blogging
0.98
blogging
0.92
blogs
0.92
Activations Density 0.010%