INDEX
Explanations
phrases related to furniture design and functionality
New Auto-Interp
Negative Logits
yourself
-0.19
yourselves
-0.18
Yourself
-0.17
myself
-0.17
اÛĮشاÙĨ
-0.14
ourselves
-0.14
ÚĨÙĨÛĮÙĨ
-0.14
imler
-0.13
nÃły
-0.12
]")]↵
-0.12
POSITIVE LOGITS
its
1.58
Its
1.20
its
1.13
Its
1.13
åħ¶
0.86
оно
0.68
å®ĥ
0.68
itself
0.67
their
0.66
åħ¶
0.59
Activations Density 1.440%