INDEX

Explanations

punctuation and foreign characters

This neuron fires most strongly on tokens that begin new sentences—i.e. punctuation marks like periods or commas and the very next word (often a discourse marker or the first word of a sentence).

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

 которые

0.89

 వారు

0.89

 તેને

0.80

 ដែល

0.79

 ಇದನ್ನು

0.75

 તેમને

0.74

 които

0.73

 обычно

0.73

 which

0.72

 వారికి

0.72

POSITIVE LOGITS

0.81

！

0.73

😜

0.71

0.68

!“

0.68

!।

0.66

！”

0.65

;-)

0.65

!”

0.61

LOL

0.60

Activations Density 21.279%