INDEX

Explanations

question and answer format

The neuron responds to unusually long tokens—whether long words (like “critical”) or long punctuation strings (like “.........”).

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

 deze

-1.38

 Benutz

-1.36

-1.33

奬

-1.33

"।

-1.32

ıla

-1.30

 phare

-1.30

燄

-1.30

 provide

-1.29

 helped

-1.27

POSITIVE LOGITS

the

1.30

of

1.20

şört

1.16

 involvement

1.16

ON

1.14

 ,‬

1.13

 ikke

1.12

よな

1.11

on

1.10

silien

1.10

Activations Density 0.000%