INDEX
Explanations
references to ducks and other poultry in various contexts
ducks and geese
New Auto-Interp
Negative Logits
Msp
-0.35
giudi
-0.35
sentimenti
-0.34
Earle
-0.34
Nerve
-0.34
narkoba
-0.33
imach
-0.32
ungkinkan
-0.31
يميديا
-0.31
odkazy
-0.31
POSITIVE LOGITS
ducks
1.13
duck
1.10
duck
0.99
geese
0.97
waterfowl
0.96
Duck
0.94
Duck
0.92
ducks
0.90
Ducks
0.88
Ducks
0.86
Activations Density 0.010%