INDEX

Explanations

statements that specify the property or characteristics of a mathematical object or set

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

 Theſe

-1.31

 myſelf

-1.27

ſelf

-1.22

 purpoſe

-1.19

 Monfieur

-1.19

 ſeveral

-1.16

Efq

-1.16

 Majefty

-1.15

 houſe

-1.13

 himſelf

-1.11

POSITIVE LOGITS

 where

0.58

 human

0.58

0.57

0.50

PreferredItem

0.50

who

0.48

for

0.48

on

0.48

↵↵

0.47

 để

0.47

Activations Density 0.035%