INDEX
Explanations
references to the word "mand" in various forms and contexts
New Auto-Interp
Negative Logits
ertz
-0.18
sing
-0.17
cia
-0.16
ahren
-0.16
sand
-0.15
mediate
-0.15
idia
-0.15
gy
-0.15
adh
-0.15
itemid
-0.14
POSITIVE LOGITS
arin
0.27
olin
0.26
ATORY
0.26
ev
0.23
itory
0.23
ala
0.22
amus
0.20
atories
0.20
ingo
0.20
rels
0.20
Activations Density 0.006%