INDEX

Explanations

movement and connection

The neuron fires on verbs in their past or past‐participle form (e.g. shaped, drawn, pulled, sculpted, showed).

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

 allarg

-1.21

 размере

-1.17

-1.13

 getrennt

-1.11

叭

-1.08

锇

-1.07

と思われます

-1.06

ৄ

-1.04

 データ

-1.02

もある

-1.02

POSITIVE LOGITS

and

1.91

out

1.89

 from

1.70

 through

1.57

 into

1.45

the

1.33

 across

1.27

——”

1.27

 LCCN

1.25

 vanaf

1.22

Activations Density 0.054%