INDEX
Explanations
specific names or terms containing the string "air"
occurrences of the word "air."
New Auto-Interp
Negative Logits
Kuh
-0.71
sylv
-0.64
URES
-0.61
Kern
-0.61
ktop
-0.59
Logged
-0.58
respons
-0.58
Contents
-0.57
enty
-0.57
mov
-0.57
POSITIVE LOGITS
bnb
1.13
neau
1.02
waves
0.99
plane
0.86
casting
0.85
fen
0.81
ship
0.81
cles
0.80
frames
0.78
planes
0.78
Activations Density 0.011%