INDEX

Explanations

"e." followed by punctuation

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

ي

1.86

Я

1.66

πο

1.54

Τα

1.52

О

1.49

ss

1.48

sh

1.48

ないので

1.46

ル

1.46

א

1.46

POSITIVE LOGITS

 तौर

1.18

 trein

1.18

 kelamin

1.18

 disclaimer

1.13

trajectory

1.11

ً

1.11

গ্রস্ত

1.10

וי

1.09

תוך

1.08

 bares

1.08

Activations Density 0.091%