INDEX

Explanations

tables and comparisons

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

ache

2.26

gaben

2.20

GCC

2.15

heets

2.08

ي

2.05

`=

1.97

മാനം

1.95

اف

1.94

˶

1.93

ospheres

1.89

POSITIVE LOGITS

 novelty

2.32

ه

2.31

ву

2.22

 prototype

2.20

mité

2.16

 progenitor

2.10

2.06

 चलाने

2.05

loin

2.05

 Fifty

2.04

Activations Density 0.021%