INDEX

Explanations

references to historical or fictional events and their contexts

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĩºäºĨ

-0.07

hid

-0.07

Ã©lÃ©

-0.07

Ãī

-0.07

 Went

-0.07

AllWindows

-0.06

amins

-0.06

Eag

-0.06

 Took

-0.06

utex

-0.06

POSITIVE LOGITS

 sein

0.16

 werden

0.15

 bleiben

0.11

 kommen

0.10

 werde

0.09

wer

0.09

HIS

0.09

 vÃ¦re

0.09

wer

0.08

 gehen

0.08

Activations Density 0.004%