INDEX
Explanations
words related to different kinds of art, such as paintings, movies, and software
references to the concept of "art."
New Auto-Interp
Negative Logits
Crosby
-0.67
cumbers
-0.65
chloride
-0.62
iod
-0.62
ker
-0.61
crest
-0.60
Aval
-0.60
snowy
-0.58
sclerosis
-0.58
defic
-0.57
POSITIVE LOGITS
ifact
1.34
illery
1.19
heid
1.17
ificial
1.13
isans
1.10
ICLE
1.06
inez
1.02
icles
0.98
ooth
0.98
oon
0.98
Activations Density 0.028%