INDEX

Explanations

possessive 's followed by a noun

The neuron activates on the possessive suffix "'s" attached to names or nouns.

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



-1.59

擽

-1.56

 Hinblick

-1.54

 bloquer

-1.52

 adoro

-1.52

URRED

-1.50

 wither

-1.49



-1.48

 terceros

-1.48

就是这样

-1.47

POSITIVE LOGITS

by

1.95

to

1.92

as

1.82

in

1.77

"]));

1.51

}}{\

1.49

 hvis

1.45

del

1.45

for

1.43

It

1.41

Activations Density 0.034%