INDEX

Explanations

No Explanations Found

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

 Ð£ÐºÑĢÐ°ÑĹÐ½Ð°

-0.07

Ð¿Ð¾Ñĩ

-0.07

lient

-0.07

reon

-0.07

 womens

-0.07

ç»ĩ

-0.07

abra

-0.07

.SE

-0.07

igo

-0.07

ãģĹãģĭ

-0.07

POSITIVE LOGITS

 probably

0.07

 Martinez

0.06

probably

0.06

Probably

0.06

ÙĨØ§

0.06

sat

0.06

 placeholders

0.06

asher

0.06

 expect

0.06

 placeholder

0.05

Activations Density 0.000%

No Known Activations

This feature has no known activations.