INDEX

Explanations

phrases that indicate the structure or organization of a 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

enne

-0.07

ÙĦÛĮÙĦ

-0.06

algo

-0.06

Ø¬Ø²

-0.06

ÑĩÐµÐ¼

-0.06

ÑĩÐ¸Ðµ

-0.06

çĥ¦

-0.06

ÙĤØ©

-0.06

owy

-0.05

 donated

-0.05

POSITIVE LOGITS

 situation

0.09

 truth

0.09

 circumstance

0.09

 reality

0.08

 scenario

0.08

 instance

0.08

enario

0.08

 uncommon

0.07

ning

0.07

truth

0.07

Activations Density 0.009%