INDEX

Explanations

walking across, from, to, along

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

ح

1.64

ai

1.51

re

1.42

it

1.38

ש

1.30

of

1.26

se

1.21

ar

1.15

ار

1.10

1.07

POSITIVE LOGITS

ές

0.97

 synchron

0.96

יות

0.96

т

0.95

 hypothes

0.92

 rozpoczę

0.91

 уви

0.91

 сдела

0.90

 reorgan

0.89

กับ

0.88

Activations Density 0.042%