INDEX

Explanations

gene

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 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

Gene

-1.05

ness

-1.03

 GENE

-0.88

 itſelf

-0.86

 faſt

-0.86

 Gene

-0.85

 Monfieur

-0.84

gene

-0.84

 fevere

-0.81

genes

-0.81

POSITIVE LOGITS

tic

0.54

cre

0.49

pp

0.48

Ass

0.47

Co

0.46

co

0.45

tically

0.44

tico

0.44

Cre

0.43

 gynnwys

0.42

Activations Density 0.336%