INDEX

Explanations

findings and evidence

The neuron detects verbs and phrases that introduce or summarize research findings or quantitative results (e.g. “shown,” “reporting,” “find,” “provides”).

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

 there

1.20

it

1.05

 they

1.03

 ότι

1.01

 that

0.97

 unequivocally

0.94

 أنه

0.92

there

0.91

:“

0.89

 दट

0.87

POSITIVE LOGITS

그리고

0.64

っぽい

0.58

的我

0.57

 wobei

0.56

堆

0.56

ゴム

0.55

List

0.55

หรือ

0.55

कैसे

0.54

そして

0.54

Activations Density 0.105%