INDEX
Explanations
words related to the color blue
references to the color blue
New Auto-Interp
Negative Logits
ROR
-0.88
rolet
-0.82
Ö¼
-0.77
ORTS
-0.75
ETF
-0.75
IVERS
-0.74
ITED
-0.74
itates
-0.74
IPM
-0.73
IFA
-0.73
POSITIVE LOGITS
prints
1.35
grass
1.24
berry
1.24
ribbon
1.09
violet
1.00
beard
0.99
berries
0.97
colored
0.94
bird
0.92
eyed
0.90
Activations Density 0.014%