INDEX

Explanations

code and URLs

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

ATH

-0.27

oogle

-0.25

è¾Ĳ

-0.25

_APB

-0.24

ognition

-0.24

Rated

-0.24

æ¶İ

-0.24

<context

-0.24

jd

-0.24

ATH

-0.23

POSITIVE LOGITS

æĺ¯è°ģ

0.26

isson

0.26

ãģ¨ãģįãģ«

0.26

Integration

0.25

çļĦèº«ä»½

0.25

TypeEnum

0.25

 corpor

0.25

ä¼ģä¸ļæıĲä¾Ľ

0.25

ilib

0.25

 experiment

0.25

Activations Density 0.001%