INDEX

Explanations

scientific/code related texts

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĿĢ

-0.28

çº¢

-0.27

èī²

-0.27

 Äĳá»ı

-0.27

ç¼Ń

-0.27

ncy

-0.25

 relat

-0.25

å¯¹ä»ĸ

-0.25

enaire

-0.24

Reducer

-0.24

POSITIVE LOGITS

icals

0.34

ToFit

0.28

ToEnd

0.26

ice

0.26

create

0.26

ä¸įéĶĪ

0.26

 Samuel

0.26

om

0.25

ç©ºåīį

0.24

íħĢ

0.24

Activations Density 0.782%