INDEX

Explanations

the word "dramatic" and the word "drama"

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

en

-0.69

-0.60

 grinder

-0.60

<blockquote>

-0.59

 Grinder

-0.58

<b>

-0.58

mik

-0.57

ten

-0.57

Privat

-0.57

 orienta

-0.57

POSITIVE LOGITS

drama

1.55

 drama

1.55

 Drama

1.43

Drama

1.43

 Dramatic

1.42

dramatic

1.41

 dramas

1.40

Dramatic

1.39

DRAM

1.35

 dramatic

1.30

Activations Density 0.009%