INDEX

Explanations

imagining, remembering, forgotten, assessing

This neuron activates on verbs in their “-ing” (gerund/present-participle) form.

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

洇

-2.52

喈

-2.36

 aisladas

-2.34

-2.31

 financieras

-2.31

 settimane

-2.30



-2.28

谖

-2.27

詎

-2.27

 adecuadas

-2.27

POSITIVE LOGITS

{~

3.45

),

3.11

and

2.36

atasaray

2.30

出発

2.11

 abide

2.08

꜆

2.05

ikuti

2.00

萵

1.96

毐

1.89

Activations Density 0.001%