INDEX

Explanations

numbers followed by that

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

るのは

0.48

率は

0.45

のため

0.42

 হেতু

0.41

ວນ

0.41

後的

0.41

 baina

0.40

 nächste

0.40

 belirt

0.39

POSITIVE LOGITS

 که

1.81

 that

1.78

 που

1.76

 которые

1.72

 التي

1.63

 الذي

1.63

 которая

1.54

që

1.50

 jotka

1.50

that

1.48

Activations Density 0.133%