INDEX

Explanations

numbers and "of"

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 konkret

-1.11

oof

-0.99

its

-0.99

unfortunately

-0.96

munity

-0.96

тие

-0.96

kub

-0.95

 tía

-0.94

 konk

-0.94

 gefahren

-0.89

POSITIVE LOGITS

optString

0.94

 lehetős

0.93

 would

0.91

ARCHITECT

0.91

 Using

0.86

 ooit

0.86

ņš

0.85

endientes

0.85

 total

0.84

 AWESOME

0.83

Activations Density 0.005%