INDEX

Explanations

when contrasted or conditional

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

一旦

0.41

 Mende

0.39

随着

0.39

 Beim

0.39

 einmal

0.38

λογ

0.38

ätter

0.38

 कोणत्याही

0.37

 പിന്നീ

0.37

ですね

0.36

POSITIVE LOGITS

 when

1.57

 cuando

1.51

 quando

1.45

when

1.44

 когда

1.38

 যখন

1.27

cuando

1.26

quando

1.25

 WHEN

1.24

 जब

1.20

Activations Density 0.067%