INDEX

Explanations

statsmodels & doctrine models

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

на

1.65

 stagnant

1.49

dır

1.45

yad

1.42

 cherish

1.33

 applaud

1.31

が多く

1.31

 bribe

1.30

 traite

1.30

POSITIVE LOGITS

َ

1.61

довой

1.53

до

1.30

ний

1.30

まで

1.27

ین

1.27

\%$

1.26

downs

1.25

='

1.24

ությ

1.23

Activations Density 0.001%