INDEX

Explanations

words related to legal language and analysis

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

-0.07

 Ð½Ð°Ð±Ð»Ñİ

-0.07

 Sheridan

-0.06

ixo

-0.06

eut

-0.06

lexical

-0.06

izable

-0.06

ymoon

-0.06

Ø´Øª

-0.06

POSITIVE LOGITS

 usually

0.11

 always

0.11

 cannot

0.10

 ALWAYS

0.10

can

0.10

OMET

0.09

 often

0.08

 tend

0.08

 rarely

0.08

always

0.08

Activations Density 0.181%