INDEX
Explanations
occurrences of the name "Morris" and related variants
New Auto-Interp
Negative Logits
cap
-0.16
czy
-0.16
oken
-0.15
tn
-0.15
å§Ĩ
-0.15
ting
-0.15
eb
-0.15
tf
-0.14
eenth
-0.14
ãĥ³ãĥĨ
-0.14
POSITIVE LOGITS
sey
0.27
seau
0.23
ons
0.18
ette
0.17
vale
0.17
νομ
0.17
ìĦľ
0.16
åĭ
0.15
esh
0.15
shal
0.15
Activations Density 0.011%