INDEX

Explanations

A

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

ex

-0.30

arton

-0.30

ivor

-0.29

aldo

-0.28

 respect

-0.27

 Leakage

-0.26

ex

-0.26

EX

-0.25

asm

-0.25

gov

-0.25

POSITIVE LOGITS

posÃ©

0.30

Ð½Ð¸

0.27

_|

0.27

pose

0.26

tensor

0.25

ä½ľ

0.25

pos

0.25

wand

0.25

 Ð¾ÑĩÐµÑĢÐµÐ´ÑĮ

0.25

Ä±klÄ±

0.24

Activations Density 0.905%