INDEX

Explanations

from ... high, latest train, will tell

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

ﭔ

1.52

п

1.45

াল

1.40

alit

1.34

々

1.33

ל

1.32

و

1.30

ار

1.30

 разрабо

1.29

il

1.28

POSITIVE LOGITS

ą

1.13

েইলি

1.10

ﺔ

1.05

 pleinement

1.01

とはいえ

1.01

रोवर

1.00

 الاجتماعية

1.00

 Premises

1.00

ತ್ತು

1.00

})$.

0.98

Activations Density 0.001%