INDEX

Explanations

code

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ist

-1.04

expert

-0.62

IST

-0.56

Expert

-0.54

 Expert

-0.52

 expert

-0.51

getDrawable

-0.45

er

-0.44

ists

-0.43

ER

-0.42

POSITIVE LOGITS

1.23

__':

1.03

 myſelf

0.98

 himſelf

0.96

ship

0.95

 Theſe

0.94

 pleaſure

0.92

 itſelf

0.91

 themſelves

0.91

 Monfieur

0.89

Activations Density 0.147%