INDEX

Explanations

X followed by list items or 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

🅔

1.31

徊

1.29

PFA

1.24

тели

1.20

 grains

1.20

 sweater

1.20

('['

1.19

ปรุง

1.18

LayoutParams

1.17

линд

1.16

POSITIVE LOGITS

ik

1.79

اد

1.61

こと

1.61

ิ

1.59

CH

1.55

fowl

1.48

ts

1.47

om

1.44

Gov

1.43

جہاں

1.41

Activations Density 0.020%