INDEX
Explanations
variations of the word "bl," indicating a focus on references to "blue."
New Auto-Interp
Negative Logits
ılıç
-0.16
_DUMP
-0.15
Gate
-0.15
neau
-0.15
lası
-0.15
šti
-0.14
leston
-0.14
AreaView
-0.14
Ä±ÅŁÄ±k
-0.14
lopen
-0.14
POSITIVE LOGITS
ues
0.33
inded
0.32
ended
0.32
onde
0.31
own
0.31
ame
0.31
azing
0.31
urred
0.31
owing
0.30
ow
0.30
Activations Density 0.017%