INDEX
Explanations
expressions of subjective experience or opinion
New Auto-Interp
Negative Logits
tera
-0.15
ÄĻk
-0.14
iable
-0.14
irl
-0.14
uki
-0.13
اÙĦب
-0.13
Composite
-0.13
achat
-0.13
ONE
-0.13
abant
-0.13
POSITIVE LOGITS
like
0.54
like
0.37
Like
0.36
Like
0.34
likes
0.34
_like
0.33
LIKE
0.32
như
0.31
.like
0.30
como
0.28
Activations Density 0.058%