Gemma, llama, LaMDA, LGA

tokens that are named entities or proper nouns (product/model names, people, places, and other capitalized terms).

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

1.92

1.57

1.55

1.42

lari

1.41

1.40

ल

1.37

یم

1.29

il

1.23

POSITIVE LOGITS

า

1.64

1.51

 σε

1.45

া

1.32

та

1.30

 في

1.30

ாதி

1.30

ا

1.27

ة

1.24

্শন

1.22

Activations Density 0.769%