INDEX

Explanations

signaling comprehension or agreement

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

 које

0.78

oğlu

0.78

 erklären

0.78

 እና

0.75

 οποία

0.75



0.74

 এটির

0.73

 yılında

0.72

 அவர்

0.72

lerini

0.72

POSITIVE LOGITS

ت

1.28

។

1.16

ي

1.15

۔

1.10

at

1.09

1.05

1.04

ali

1.02

ach

0.98

т

0.98

Activations Density 0.031%