INDEX

Explanations

adverb or determiner followed by a verb or noun

The neuron strongly fires on common function words—especially adverbs (e.g. “sometimes,” “thus,” “completely,” “soon”) and auxiliary or modal verbs (e.g. “does,” “will,” “having”) that structure and qualify sentences.

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

to

-1.81

on

-1.38

不斷

-1.27

فقط

-1.26

Dobrý

-1.24

ようになった

-1.20

웹

-1.20

جموعة

-1.19

艱

-1.16

鴣

-1.16

POSITIVE LOGITS

hata

1.40

 السياس

1.40

again

1.36

too

1.28

portation

1.27

pitre

1.27

while

1.26

 машину

1.26

ciled

1.23

Addo

1.23

Activations Density 0.440%