INDEX
Explanations
occurrences of the word "form" and its variations in different contexts
New Auto-Interp
Negative Logits
era
-0.17
isa
-0.15
ender
-0.15
at
-0.14
boo
-0.14
_inches
-0.14
oi
-0.14
ot
-0.14
976
-0.14
eri
-0.14
POSITIVE LOGITS
ulating
0.26
ulates
0.23
bonds
0.23
-formed
0.21
part
0.20
formed
0.20
formation
0.20
basis
0.20
formed
0.19
ulators
0.19
Activations Density 0.025%