INDEX
Explanations
references to the number six and its variations
New Auto-Interp
Negative Logits
ont
-0.17
ports
-0.17
iams
-0.16
led
-0.15
439
-0.15
Kushner
-0.15
lint
-0.15
aren
-0.15
loys
-0.15
ived
-0.14
POSITIVE LOGITS
teenth
0.37
ties
0.31
teen
0.29
ti
0.29
ty
0.27
sense
0.23
TY
0.21
six
0.20
iang
0.19
tel
0.19
Activations Density 0.116%