INDEX
Explanations
references to crustaceans or related sea creatures
New Auto-Interp
Negative Logits
wolves
-0.16
deer
-0.15
fleece
-0.15
snake
-0.15
illard
-0.15
bird
-0.15
sheep
-0.14
bark
-0.14
slash
-0.14
ewe
-0.13
POSITIVE LOGITS
shrimp
0.23
shells
0.22
antenn
0.20
shell
0.20
èŀ
0.18
cray
0.18
-shell
0.17
Crab
0.17
å¾Ĵ
0.16
ayload
0.16
Activations Density 0.027%