INDEX
Explanations
phrases that indicate future actions or offers of assistance
New Auto-Interp
Negative Logits
Heard
-0.18
remembered
-0.15
imeo
-0.14
zn
-0.14
got
-0.14
aylor
-0.14
FormField
-0.14
FIELDS
-0.14
ochen
-0.14
zek
-0.13
POSITIVE LOGITS
find
0.21
finds
0.19
finde
0.18
inds
0.17
fine
0.17
finer
0.16
/latest
0.16
Minds
0.15
pel
0.15
see
0.15
Activations Density 0.045%