INDEX

Explanations

special characters or symbols in the text

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

inke

-0.07

 kÃª

-0.07

bled

-0.06

INUE

-0.05

.Dom

-0.05

assandra

-0.05

 supermarkets

-0.05

èĢĥ

-0.05

 encodeURIComponent

-0.05

 nÃ¡d

-0.05

POSITIVE LOGITS

 Moderator

0.19

 moderator

0.19

 Moder

0.18

 moderators

0.18

Moder

0.17

 moderation

0.17

 mods

0.15

 Mods

0.15

 moder

0.14

 moderated

0.14

Activations Density 0.003%