INDEX
Explanations
phrases related to movement or progression from one point to another
the phrase "all the way" in various contexts
New Auto-Interp
Negative Logits
ĪĴ
-0.89
ĸļ
-0.81
ister
-0.78
igel
-0.78
erves
-0.75
uster
-0.73
orem
-0.71
erve
-0.69
Scene
-0.67
oggle
-0.66
POSITIVE LOGITS
forth
0.84
forward
0.83
ward
0.80
points
0.80
Jordan
0.76
finding
0.73
around
0.73
point
0.72
PORT
0.63
fare
0.63
Activations Density 0.019%