INDEX

Explanations

a variety of seemingly unrelated character sequences, often including "ar", "ware", possibly involving code, and possibly involving names

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

 ſeveral

-0.89

 myſelf

-0.88

ſelves

-0.87

 Diſ

-0.83

ſelf

-0.82

 Monfieur

-0.82

 ſmall

-0.81

 itſelf

-0.78

 Anſ

-0.77

neſs

-0.77

POSITIVE LOGITS

la

0.66

lah

0.63

lar

0.59

LA

0.59

ла

0.59

lan

0.57

lag

0.54

WriteTagHelper

0.52

ilar

0.52

Lag

0.52

Activations Density 0.246%