INDEX

Explanations

the word "affect" and words that have similar meanings

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

 affect

-2.55

 affects

-2.22

affect

-2.14

 Affect

-2.11

 affecting

-2.05

 AFFECT

-1.94

 affected

-1.88

 Affects

-1.77

Affect

-1.73

 Affecting

-1.65

POSITIVE LOGITS

 wireType

0.66

 Réponses

0.59

hynch

0.59

addCriterion

0.57

 vermelha

0.55

writeHead

0.55

MessageTagHelper

0.54

DIPSETTING

0.53

AddTagHelper

0.53

IVEREF

0.53

Activations Density 0.463%