INDEX

Explanations

numbers containing a 0

numbers or data

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

Efq

-1.30

 itſelf

-1.24

 myſelf

-1.23

 Monfieur

-1.13

ſelves

-1.12

 Theſe

-1.10

ſelf

-1.07

 themſelves

-1.06

 Reſ

-1.06

 himſelf

-1.02

POSITIVE LOGITS

.,

0.59

0.58

.:

0.56

-$

0.55

0.54

,$

0.52

$$

0.51

$.

0.51

0.50

Activations Density 0.544%