INDEX
Explanations
instances of the word "just" in various contexts
New Auto-Interp
Negative Logits
ONLY
-0.19
only
-0.17
Only
-0.17
Only
-0.17
only
-0.15
_only
-0.15
ijken
-0.15
rum
-0.14
orthy
-0.14
ard
-0.14
POSITIVE LOGITS
plain
0.26
sort
0.21
Plain
0.21
plain
0.20
simply
0.18
chalk
0.18
happened
0.17
Plain
0.17
cannot
0.16
seems
0.16
Activations Density 0.050%