INDEX

Explanations

questions starting with what how are where

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

aneity

-1.27

 belangrijkste

-1.19

-\\

-1.16

Î

-1.12

 コート

-1.12

:%.

-1.11

mathrm

-1.10

⊖

-1.08

>?

-1.06

fah

-1.06

POSITIVE LOGITS

 pocas

1.25

zsh

1.23

1.16

 chaque

1.16

 моей

1.15

 meiner

1.11

 habiendo

1.06

 държа

1.05

古屋

1.05

 modernos

1.03

Activations Density 0.128%