INDEX

Explanations

actor

The neuron fires strongly on occurrences of the word “actor” (and its plural “actors”).

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

’

-2.30

的大

-2.08

uellement

-2.02

⇘

-2.02

りました

-2.02

ších

-1.84

ŚĆ

-1.82

rocław

-1.77

ίας

-1.77

ませんが

-1.76

POSITIVE LOGITS

2.38

you

2.30

檮

2.27

',

2.22

𖥧

2.19

</em>

2.14

肫

2.11

 tornar

2.09

 ilumina

2.08

 wilden

2.02

Activations Density 0.012%