INDEX
Explanations
structural components and features of objects or systems
New Auto-Interp
Negative Logits
ataka
-0.17
indi
-0.16
whose
-0.15
tet
-0.15
deren
-0.14
HeaderText
-0.14
ctl
-0.14
inha
-0.14
whose
-0.14
.Std
-0.13
POSITIVE LOGITS
thereof
0.19
/front
0.18
/end
0.18
sequ
0.17
/back
0.17
/top
0.16
-mounted
0.16
erv
0.16
-facing
0.15
-most
0.15
Activations Density 0.114%