INDEX

Explanations

punctuation and 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

 compared

-0.20

 versus

-0.16

 unlike

-0.15

vs

-0.15

 Unlike

-0.15

 Compared

-0.14

 opposed

-0.13

Unlike

-0.13

 differs

-0.12

VS

-0.11

POSITIVE LOGITS

noch

0.10

ibel

0.09

tem

0.09

–and

0.09

 nonetheless

0.09

Tem

0.09

Php

0.09

/Index

0.09

 nevertheless

0.08

esi

0.08

Activations Density 0.432%