INDEX

Explanations

again, also, further

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lably

-0.97

 that

-0.95

 barcos

-0.94

郓

-0.93

 upor

-0.93

 EVERY

-0.93

 DEVICES

-0.92

marily

-0.91

 biela

-0.91

ál

-0.90

POSITIVE LOGITS

 nuevamente

1.18

 tambien

1.13

 again

1.06

 Again

1.02

 novamente

1.00

 ďal

1.00

 även

0.98

では

0.97

 further

0.96

 erneut

0.96

Activations Density 0.005%