INDEX

Explanations

key names and terms related to societal commentary and critique

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

odo

-0.10

 understandably

-0.08

ãģłãĤįãģĨ

-0.07

ODO

-0.06

 mÃ¼ÅŁ

-0.06

 alone

-0.06

avenport

-0.06

,...↵↵

-0.06

arga

-0.06

Ð½Ð¾Ñĩ

-0.06

POSITIVE LOGITS

 actually

0.26

actually

0.22

 Actually

0.21

Actually

0.19

 actual

0.18

å®ŀéĻħ

0.17

 aslÄ±nda

0.15

åħ¶å®ŀ

0.15

actual

0.15

 reality

0.15

Activations Density 0.008%