INDEX
Explanations
proper nouns related to individuals named Ben
the name "Ben" in various contexts
New Auto-Interp
Negative Logits
Division
-0.75
cone
-0.72
overw
-0.72
landslide
-0.70
division
-0.70
worker
-0.70
disposal
-0.70
swoop
-0.67
Wings
-0.67
gallery
-0.66
POSITIVE LOGITS
Ben
3.73
Ben
1.58
ben
1.52
Benjamin
1.48
BEN
1.30
Jen
1.28
Martin
1.26
Jeff
1.21
Bernie
1.20
Bern
1.19
Activations Density 0.004%