INDEX

Explanations

before numerical lists or specific phrases

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

${_

2.11

셸

2.02

 piş

1.97

 教え

1.90

十壹章

1.85

 nghĩ

1.84

 thuyền

1.82

:',

1.79

injlim

1.79

ורים

1.78

POSITIVE LOGITS

and

1.41

ude

1.21

ral

1.21

ne

1.21

sm

1.18

erçe

1.17

so

1.16

uhan

1.15

len

1.14

ramp

1.13

Activations Density 0.948%