INDEX

Explanations

state of being, becoming

The neuron fires strongly on personal-pronoun usage (e.g. “I,” “you,” “we”), marking explicit first- or second-person references.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

RBI

0.59

 দিবে

0.57

MONG

0.55

PING

0.54

 здійсню

0.54

configuring

0.53

чү

0.52

ใช้

0.52

 নেওয়ার

0.52

คา

0.52

POSITIVE LOGITS

 become

1.28

 geworden

1.27

 становятся

1.19

 becomes

1.18

 становится

1.13

 becoming

1.11

 olmuş

1.11

 became

1.08

 бывают

1.06

becomes

1.05

Activations Density 0.287%