INDEX

Explanations

pronouns and demonstratives

The neuron fires strongly on first‐person, self‐referential statements—especially “I” plus a verb expressing intent or action.

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

嘮

-1.07

kém

-1.03

 निम्नलिखित

-1.03

styp

-0.99

그러나

-0.98

iric

-0.97

打量

-0.93

IPPI

-0.93

保养

-0.93

 רוצה

-0.92

POSITIVE LOGITS

it

2.81

its

2.06

 그것

1.55

 siihen

1.40

 those

1.39

它

1.34

它

1.34

 оно

1.30

 его

1.27

 её

1.24

Activations Density 0.083%