INDEX

Explanations

is followed by a word

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

на

1.27

ت

1.26

어야

1.23

oqu

1.20

komen

1.13

ोत्तर

1.13

sto

1.08

いろいろ

1.07

 действи

1.05

いろんな

1.05

POSITIVE LOGITS

いた

1.30

 तरह

1.19

니다

1.17

 Međutim

1.04

 wrongdoing

1.02

லாமல்

1.02

اد

0.97

⟣

0.95

 ventures

0.94

بار

0.92

Activations Density 0.055%