INDEX

Explanations

list items and code snippets

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

ی

3.16

یان

2.82

मध्ये

2.78

ल

2.67

theless

2.64

রকম

2.57

tı

2.52

هما

2.50

‍♀️

2.50

ℎ

2.48

POSITIVE LOGITS

quela

3.32

きた

2.93

্কর

2.67

boldsymbol

2.52

가

2.33

ികിത്സ

2.27

ान

2.25

водит

2.24

ır

2.23

هم

2.23

Activations Density 0.077%