INDEX

Explanations

connecting conjunctions

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

 knew

-1.26

or

-1.20

on

-1.17

 различни

-1.16

 дуже

-1.09

 moeilijk

-1.08

𝟐

-1.07

 когато

-1.06

;;)

-1.05

 Що

-1.03

POSITIVE LOGITS

ďaka

1.36

Plenty

1.31

があり

1.25

 Meanwhile

1.22

轳

1.19

ちなみに

1.19

 puisque

1.15

 obstin

1.14

 meanwhile

1.14

しかし

1.14

Activations Density 0.069%