INDEX
Explanations
words related to vertebrates and their anatomical features
New Auto-Interp
Negative Logits
Banc
-0.17
dbus
-0.17
_Il
-0.16
rien
-0.16
rych
-0.16
ry
-0.15
rst
-0.15
наÑĩе
-0.14
yo
-0.14
rut
-0.14
POSITIVE LOGITS
ebra
0.36
igo
0.27
icle
0.25
igin
0.23
ically
0.21
Vert
0.20
IGO
0.20
ical
0.20
vert
0.19
umn
0.19
Activations Density 0.008%