INDEX

Explanations

such harmful information

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ि

2.45

ার

2.34

शिप

2.30

⎛

2.27

্শন

2.27

ம்

2.25

ťou

2.20

ুপ্ত

2.17

০০

2.16

setCharacter

2.15

POSITIVE LOGITS

ਆਂ

3.04

2.65

jata

2.64

ools

2.51

anski

2.44

 palav

2.39

sy

2.37

tan

2.35

ỡi

2.34

sah

2.27

Activations Density 0.124%