INDEX
Explanations
discussions about personal responsibility and making excuses
New Auto-Interp
Negative Logits
bkz
-0.65
itſelf
-0.60
myſelf
-0.56
becauſe
-0.55
OGND
-0.53
ſelves
-0.53
***/
-0.52
raiſ
-0.52
ksikon
-0.50
ſhe
-0.49
POSITIVE LOGITS
next
1.23
next
1.04
Next
0.93
Next
0.93
下次
0.93
nästa
0.88
prochaine
0.84
prossima
0.82
næste
0.76
nächste
0.75
Activations Density 0.106%