INDEX

Explanations

verbs describing actions or states

The neuron strongly activates on meaningful content words—especially longer, technical or descriptive nouns, verbs, and adjectives—rather than on common function words.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 then

-1.36

 these

-1.33

 this

-1.29

 infatti

-1.25

 those

-1.24

 tersebut

-1.18

 Giochi

-1.14

 đây

-1.13

 which

-1.13

 inoltre

-1.12

POSITIVE LOGITS

 vermelhas

1.16

 없습니다

1.15

 dianteira

1.11

کہ

1.11

Barium

1.07

ทั้ง

1.07

%;

1.06

汙

1.04

 brancas

1.04

 poetas

1.03

Activations Density 0.240%