INDEX

Explanations

LLaMA and Vicuna models

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

yah

1.46

ي

1.38

yek

1.31

ా

1.31

1.30

ی

1.28

েরও

1.27

yal

1.27

tı

1.26

yat

1.24

POSITIVE LOGITS

 എന്നാല്‍

1.39

因為

1.38

ise

1.33

ce

1.28

 أيضاً

1.27

 എന്നാൽ

1.26

 darah

1.23

ScriptAssemblies

1.23

cua

1.19

因此

1.16

Activations Density 0.156%