INDEX
Explanations
phrases related to coercion or forceful actions
gerunds or present participles of verbs
New Auto-Interp
Negative Logits
Gates
-0.61
Beaut
-0.61
Bush
-0.60
publicly
-0.59
bush
-0.57
merch
-0.56
street
-0.56
Nob
-0.55
book
-0.55
trash
-0.54
POSITIVE LOGITS
cing
4.41
ced
2.95
ces
2.32
cer
1.72
cers
1.70
cible
1.55
icing
1.54
ce
1.50
cence
1.48
cest
1.38
Activations Density 0.006%