INDEX

Explanations

references to time duration or experience

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

anÃ¡

-0.06

ÑģÐºÐ¾ÑĢ

-0.06

 zase

-0.06

Ã³j

-0.06

endale

-0.06

urgence

-0.05

ayla

-0.05

eward

-0.05

 instead

-0.05

 ÑģÐºÐ¾ÑĢ

-0.05

POSITIVE LOGITS

 longer

0.12

 longest

0.11

 been

0.10

 dating

0.10

 Longer

0.09

been

0.09

 Been

0.09

 ever

0.09

Been

0.08

 Accum

0.08

Activations Density 0.083%