INDEX

Explanations

personal pronouns

The neuron strongly activates on personal/pronominal references (object and possessive pronouns like me, you, him, her, them, yourself, your).

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

多次

-1.23

 aktive

-1.21

 الذي

-1.20

 notre

-1.20

my

-1.20

our

-1.17

 سعی

-1.16

Il

-1.11

によく

-1.11

 dois

-1.10

POSITIVE LOGITS

 when

1.45

верка

1.20

 웹툰

1.18

なります

1.18

izante

1.17

 sebuah

1.16

spedes

1.13

回戦

1.12

ciful

1.11

wszy

1.11

Activations Density 0.030%