INDEX

Explanations

apostrophes followed by specific tokens

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

১

1.61

ва

1.55

 Перейти

1.39

 लिए

1.37

িক

1.35

на

1.34

ент

1.33

,}$

1.33

экс

1.31

ಗ

1.30

POSITIVE LOGITS

hwar

1.55

 vilket

1.51

с

1.49

主任

1.49

esse

1.47

 macam

1.45

ח

1.44

 tako

1.43

д

1.41

bottomMargin

1.40

Activations Density 0.012%