INDEX

Explanations

snippets of code, syntax, or technical language

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 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

 trac

-0.75

 Schweitzer

-0.70

vastatin

-0.65

agrad

-0.64

lccccc

-0.63

truc

-0.62

ồn

-0.61

geç

-0.61

prec

-0.60

 Dolores

-0.60

POSITIVE LOGITS

ey

1.28

Chy

1.22

SPY

1.20

yy

1.19

Jy

1.19

 startY

1.19

Bly

1.18

Gy

1.17

VY

1.17

JY

1.17

Activations Density 10.991%