INDEX
Explanations
mentions of fruit in various contexts
New Auto-Interp
Negative Logits
\{\\-0.48
SUPERIOR
-0.47
letic
-0.47
standing
-0.46
Nimbus
-0.45
surla
-0.44
superior
-0.44
Westport
-0.42
AssemblyVersion
-0.42
mental
-0.42
POSITIVE LOGITS
fruit
0.99
Fruit
0.93
fruit
0.91
Fruit
0.90
FRUIT
0.82
fruits
0.73
Fruits
0.64
Fruits
0.64
<tr>
0.63
frutta
0.60
Activations Density 0.027%