INDEX

Explanations

wonder followed by interrogatives or conditionals

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

是用

1.54

是从

1.33

äl

1.31

 untouched

1.20

née

1.18

 الصور

1.15

燹

1.15

스러운

1.14

╡

1.13

руются

1.13

POSITIVE LOGITS

ва

1.38

ים

1.31

aneous

1.27

 payoff

1.26

 fate

1.25

<bos>

1.23

 indo

1.23

endan

1.22

เรื่อง

1.22

豊

1.21

Activations Density 0.002%