INDEX
Explanations
phrases or discussions related to storytelling and narratives
New Auto-Interp
Negative Logits
både
-0.17
both
-0.17
ambos
-0.17
BOTH
-0.16
обо
-0.16
Both
-0.15
both
-0.15
Both
-0.15
caffold
-0.15
_both
-0.15
POSITIVE LOGITS
those
0.27
something
0.24
those
0.21
Those
0.20
another
0.19
Those
0.19
us
0.18
ourselves
0.17
my
0.17
why
0.17
Activations Density 0.224%