INDEX

Explanations

nouns followed by verbs

This neuron fires on exported Go identifiers (package-level names beginning with an uppercase letter).

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

 Feels

-1.05

徒歩

-1.04

thx

-1.01

 parecer

-1.00

を入れ

-0.98

 vertelt

-0.96

varlak

-0.96

 hornear

-0.94

%.

-0.93

 inoltre

-0.93

POSITIVE LOGITS

is

1.46

 would

1.27

倘

1.20

という

1.19

以下

1.16

 refers

1.13

 will

1.13

 This

1.10

・・・

1.09

は

1.07

Activations Density 0.092%