INDEX

Explanations

specific characters and symbols, likely focusing on non-English or special text elements

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

 âĢ¦

-0.08

..

-0.08

--

-0.08

—

-0.08

 âĢ¦.

-0.07

...

-0.06

 âĢ¦↵↵

-0.06

 --↵

-0.06

 —↵

-0.06

))[

-0.06

POSITIVE LOGITS

 utilizing

0.08

 utilization

0.07

 hence

0.07

 utilized

0.07

 utilize

0.07

Util

0.07

 gotta

0.07

_Util

0.07

 ourselves

0.07

 Util

0.06

Activations Density 0.001%