INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 myſelf

-1.25

 Theſe

-1.13

Efq

-1.13

 Jefus

-1.11

 Diſ

-1.08

 Monfieur

-1.05

 ſta

-1.04

 raiſ

-1.04

 himſelf

-1.02

 whoſe

-1.02

POSITIVE LOGITS

...

0.54

0.52

\},

0.45

landes

0.45

NORM

0.45

 mencetak

0.45

Norma

0.44

()]

0.44

:],

0.43

0.42

Activations Density 0.000%

No Known Activations