INDEX

Explanations

before followed by action

The neuron fires on verbs (especially present‐participles and key action words) that describe events or actions in the text.

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

 when

-1.91

but

-1.70

 only

-1.67

 then

-1.53

 acercarse

-1.44

 both

-1.43

not

-1.38

 many

-1.34

 тогда

-1.34

 than

-1.33

POSITIVE LOGITS

蠵

1.38

syk

1.31

 viande

1.31

 outros

1.30

 rendement

1.23

läs

1.20

tettu

1.20

 patrie

1.18

 situe

1.17

鋨

1.17

Activations Density 0.043%