INDEX
Explanations
positive sentiments related to completion and value
Expressing gratitude and appreciation
thank you / appreciated
New Auto-Interp
Negative Logits
Мексичка
-0.76
'){
-0.70
")){
-0.70
"){
-0.69
'),
-0.67
"),
-0.67
]--;
-0.66
$")
-0.65
Fandom
-0.65
），
-0.64
POSITIVE LOGITS
Thank
0.88
thank
0.87
!
0.84
Thank
0.79
THANK
0.78
merci
0.75
Sincerely
0.74
<eos>
0.74
Thanks
0.73
!!
0.72
Activations Density 0.198%