INDEX
Explanations
occurrences of the word "some"
New Auto-Interp
Negative Logits
igli
-0.17
Eta
-0.15
appa
-0.15
ầu
-0.15
ameleon
-0.15
rong
-0.15
WithError
-0.14
δή
-0.14
rese
-0.14
ahoo
-0.14
POSITIVE LOGITS
Matters
0.19
matters
0.18
Distance
0.17
ICS
0.17
leground
0.17
distance
0.17
ja
0.15
æĿ¾
0.15
matter
0.15
Matter
0.14
Activations Density 0.006%