INDEX

Explanations

words with positive or negative sentiment

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LEn

-0.58

SPATH

-0.56

 soggior

-0.55

+#+#

-0.54

/**

-0.52

zzleHttp

-0.52

#![

-0.52

pez

-0.50

tembro

-0.50

Conta

-0.49

POSITIVE LOGITS

 '\\;'

0.68

saw

0.67

ніципалі

0.66

itarianism

0.65

saw

0.63

原始内容存档于

0.61

 visually

0.61

 seen

0.59

seeing

0.59

Saw

0.59

Activations Density 0.340%