INDEX

Explanations

references to legal roles or entities, specifically those involving attorneys or legal representation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm

Prompts (Dashboard)

32,768 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

torch.float32

Hook Name

blocks.0.hook_mlp_out

Hook Layer

Architecture

standard

Context Size

128

Dataset

EleutherAI/the_pile_deduplicated

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 bothered

-1.62

 loose

-1.55

 brid

-1.47

 swollen

-1.46

 swelling

-1.46

 rolling

-1.44

 small

-1.42

 brow

-1.41

itter

-1.40

 Behavior

-1.39

POSITIVE LOGITS

ificial

1.97

gio

1.96

ware

1.94

ikel

1.86

esan

1.85

etica

1.80

haus

1.78

vÃ¤

1.77

vre

1.70

 histor

1.69

Activations Density 0.082%

references to legal roles or entities, specifically those involving attorneys or legal representation

No Comments

No Known Activations