INDEX

Explanations

Past tense/participle suffixes

New Auto-Interp

Configuration

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

udios

-0.06

 questi

-0.06

.design

-0.06

 Origins

-0.06

 trafficking

-0.06

 penalty

-0.06

 plea

-0.06

POSITIVE LOGITS

()='

0.07

interested

0.06

lä

0.06

 mlad

0.06

خب

0.06

áb

0.06

 Residential

0.06

_strlen

0.06

 žid

0.06

 vysok

0.06

Activations Density 0.125%