INDEX
Explanations
instances of repetition and sequencing in phrases
New Auto-Interp
Negative Logits
irse
-0.14
ime
-0.14
luck
-0.14
reon
-0.14
ÃĩaÄŁ
-0.14
ëĿ¼ëıĦ
-0.14
оÑĢÑĤÑĥ
-0.13
oga
-0.13
lea
-0.13
ÏĦία
-0.13
POSITIVE LOGITS
vo
0.57
boom
0.53
Vo
0.48
Bam
0.45
Boom
0.45
bam
0.44
BAM
0.44
prest
0.43
vo
0.42
bang
0.42
Activations Density 0.253%