INDEX

Explanations

sentences that contain a high ratio of pronouns and auxiliary verbs, often indicating a conversational tone or personal narrative

when

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

 appeal

-0.45

 Charm

-0.44

 Appeal

-0.43

те

-0.42

 book

-0.41

 instability

-0.41

èdia

-0.41

vol

-0.40

 prostu

-0.40

찰

-0.40

POSITIVE LOGITS

 mergeFrom

1.03

 Мексичка

0.82

#+#

0.79

 незавершена

0.79

enumi

0.78

 onCancelled

0.77

 للاسماء

0.77

 مشين

0.77

tagHelperRunner

0.75

<?

0.75

Activations Density 1.692%