INDEX

Explanations

seemingly random punctuation and sentence fragments within the text

sentence fragments

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

Negative Logits

principalColumn

-0.77

AndEndTag

-0.65

Gweler

-0.63

IntoConstraints

-0.61

 autorytatywna

-0.59

 createSprite

-0.58

 للمعارف

-0.57

HasMaxLength

-0.57

Enllaces

-0.55

withIdentifier

-0.54

POSITIVE LOGITS

<bos>

0.57

########.

0.56

 Kine

0.55

resh

0.54

 "../../../

0.53

яз

0.52

 Sopho

0.51

amilya

0.51

áso

0.51

PMG

0.51

Activations Density 1.719%