INDEX
Explanations
phrases or words related to the color green
references to the color green
New Auto-Interp
Negative Logits
lator
-0.94
DSM
-0.80
DOM
-0.69
Anat
-0.68
Cyrus
-0.67
suscept
-0.67
Myster
-0.67
Words
-0.66
hid
-0.65
Twain
-0.65
POSITIVE LOGITS
green
3.58
green
2.59
greens
2.39
GREEN
2.23
Green
2.22
Green
2.21
yellow
2.06
blue
1.98
purple
1.86
orange
1.83
Activations Density 0.017%