INDEX

Explanations

small amounts or numbers

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

 luego

1.41

 μην

1.32

 κι

1.31

 واله

1.27

 quieran

1.27

岖

1.26

 teniendo

1.25

িতা

1.24

বিদ

1.23

ൻ

1.23

POSITIVE LOGITS

$(<

2.38

(\<

1.29

🤏

1.25

(<

1.19

 handful

1.14

 scant

1.13

 fief

1.06

मात्र

1.06

 wenigen

1.05

 less

1.04

Activations Density 0.391%