INDEX

Explanations

surfaces

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

 surfaces

-1.10

 bodies

-0.79

 body

-0.75

 Surfaces

-0.75

surfaces

-0.73

things

-0.73

bodies

-0.68

 Body

-0.66

Body

-0.64

esticides

-0.63

POSITIVE LOGITS

principalColumn

0.75

 zewnętrzne

0.63

Vidite

0.63

AutoField

0.63

mybatisplus

0.62

 nuages

0.60

 quelcon

0.57

 larmes

0.57

 fondament

0.55

 nahilalakip

0.55

Activations Density 0.207%