INDEX
Explanations
mentions of policies or decisions being scrapped
words related to the concept of "scrapping" or removing something, often in a legal or procedural context
New Auto-Interp
Negative Logits
scl
-0.71
ness
-0.69
soever
-0.67
iquid
-0.65
supremacy
-0.64
icity
-0.64
imentary
-0.63
icate
-0.62
bodies
-0.61
enstein
-0.61
POSITIVE LOGITS
ppy
1.36
ppers
1.26
pping
1.23
pper
1.18
pling
1.13
ptions
1.03
pton
1.03
bably
0.97
olitics
0.96
pped
0.96
Activations Density 0.056%