INDEX

Explanations

activities and processes

The neuron strongly activates on words ending in “-ing” (i.e. gerund or present-participle forms).

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

 these

-1.46

したのが

-1.45

した後

-1.43

vuo

-1.37

 that

-1.37

 THEOREM

-1.37

還會

-1.32

內的

-1.32

romas

-1.31

 informée

-1.30

POSITIVE LOGITS

peteer

1.60

."

1.49

siasme

1.38

 ſame

1.37

OTHY

1.34

没有任何

1.34

ierter

1.32

犴

1.32

 molti

1.30

lète

1.30

Activations Density 0.361%