INDEX
Explanations
occurrences of the letter 'p'
New Auto-Interp
Negative Logits
themſelves
-0.65
raiſ
-0.64
houſe
-0.64
niedersachsen
-0.62
ſel
-0.62
avoient
-0.62
ſmall
-0.61
myſelf
-0.61
izel
-0.60
*/;
-0.59
POSITIVE LOGITS
p
2.77
p
1.64
p
1.37
р
1.18
pp
1.16
pS
1.13
getP
1.06
pV
0.98
pg
0.95
pM
0.94
Activations Density 0.197%