INDEX
Explanations
references to body parts, in particular, the nose
references to the word "nose" in various contexts
New Auto-Interp
Negative Logits
ILCS
-0.79
ERAL
-0.75
icity
-0.72
aneously
-0.72
iary
-0.71
20439
-0.69
ACPI
-0.68
Leader
-0.66
Avg
-0.65
Volunte
-0.65
POSITIVE LOGITS
cone
1.10
cone
1.02
bones
0.98
cones
0.97
nose
0.92
ble
0.86
wash
0.85
pipe
0.83
beard
0.82
pier
0.81
Activations Density 0.006%