INDEX
Explanations
connections to personal experiences of pain and loss
New Auto-Interp
Negative Logits
everyone
-0.22
everybody
-0.20
quite
-0.20
several
-0.19
every
-0.17
everything
-0.17
everywhere
-0.17
Several
-0.17
two
-0.17
both
-0.17
POSITIVE LOGITS
ANY
0.43
any
0.35
EITHER
0.31
either
0.31
ANY
0.30
anything
0.29
ä»»ä½ķ
0.29
(any
0.29
any
0.29
à¹ĥà¸Ķ
0.28
Activations Density 0.810%