INDEX

Explanations

dictionary and map data structures

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

 continuité

0.42

 núi

0.40

 gunung

0.40

Kuota

0.40

 رقم

0.40

cigarettes

0.40

 "*");

0.38

騾

0.38

ᚕ

0.38

ChessBot

0.38

POSITIVE LOGITS

 dictionary

2.16

 dict

2.05

 Dictionary

1.99

dict

1.95

 dictionaries

1.93

字典

1.93

 Dict

1.85

dictionary

1.84

Dictionary

1.84

Dict

1.83

Activations Density 0.111%