INDEX

Explanations

It explains things

This neuron detects occurrences of the pronoun “it.”

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

0.42

及び

0.42

と共に

0.42

↵

0.39

のです

0.38

 وعلى

0.37

及

0.37

および

0.36

 কর্তৃক

0.36

POSITIVE LOGITS

 Happened

0.52

tait

0.45

Οι

0.45

 হইতেছে

0.43

 Είναι

0.43

comme

0.43

 happened

0.42

 sucedido

0.42

 Надо

0.42

hehe

0.42

Activations Density 0.434%