INDEX

Explanations

straying or deviating

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

صرية

0.42

мень

0.41

醃

0.39

ransfer

0.39

令

0.39

្អ

0.39

rugated

0.38

 brillante

0.38

selectTable

0.37

лично

0.37

POSITIVE LOGITS

 stray

1.51

 deviation

1.46

 deviate

1.41

 deviated

1.37

 deviates

1.34

 devi

1.32

 deviations

1.30

 откло

1.28

 Deviation

1.24

 wandered

1.23

Activations Density 0.028%