INDEX
Explanations
conjunctions and other linking words that connect ideas or clauses
New Auto-Interp
Negative Logits
ieres
-0.16
ocale
-0.16
marca
-0.15
arine
-0.15
raries
-0.15
bard
-0.14
ugins
-0.14
exus
-0.14
ariat
-0.14
ucene
-0.13
POSITIVE LOGITS
ily
0.14
Apt
0.14
ji
0.13
Fraction
0.13
considering
0.13
aver
0.13
леÑĩ
0.13
_fraction
0.13
sted
0.13
eli
0.13
Activations Density 0.316%