INDEX

Explanations

questions about usage or requirements

The neuron responds to common function words (pronouns and auxiliary/helping verbs like “I,” “you,” “have,” “do,” “using,” etc.).

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

 only

-1.85

 должен

-1.66

-1.63

 also

-1.62

。"

-1.59

Only

-1.52

-1.47

}=\

-1.45

Both

-1.41

by

-1.35

POSITIVE LOGITS

 such

1.59

 this

1.46

Ծանոթ

1.42

nias

1.40

of

1.40

IMON

1.34

 they

1.33

 szczegól

1.33

greja

1.30

颪

1.30

Activations Density 0.060%