INDEX

Explanations

words and phrases about potential harm and virus infections

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

 affected

-1.17

 afflicted

-1.06

 impacted

-1.04

affected

-1.01

Affected

-1.00

 Affected

-1.00

protoimpl

-0.86

 afectada

-0.85

 troubled

-0.81

 AFFECT

-0.81

POSITIVE LOGITS

 別注

0.50

ContentAsync

0.50

ClientSize

0.49

//});

0.49

 afield

0.45

tė

0.44

 quoque

0.43

 boyfriends

0.43

 løs

0.42

 uncles

0.42

Activations Density 1.881%