INDEX

Explanations

canon

New Auto-Interp

Configuration

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 youngest

-0.07

 ослож

-0.07

<translation

-0.06

στρο

-0.06

.activities

-0.06

 bothered

-0.06

 thirteen

-0.06

_branch

-0.06

.Some

-0.06

POSITIVE LOGITS

canonical

0.08

 Canon

0.08

 canonical

0.08

炮

0.07

Canon

0.07

 canon

0.07

 Leonardo

0.07

dao

0.07

ardon

0.07

anon

0.07

Activations Density 0.005%

No Known Activations