INDEX

Explanations

terms related to the COVID-19 pandemic and its impacts

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

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm

Prompts (Dashboard)

32,768 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

torch.float32

Hook Name

blocks.2.hook_resid_post

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

ĭ

-3.03

ı

-2.78

¿½

-2.67

ģ

-2.65

į

-2.62

ŀ

-2.61

ľĵ

-2.58

↵

-2.58

↵

-2.58

POSITIVE LOGITS

 pandemic

2.00

ulent

1.79

 COVID

1.74

OVID

1.65

 coronavirus

1.63

izumab

1.58

ariat

1.57

ulence

1.55

 season

1.51

avirus

1.45

Activations Density 0.325%

terms related to the COVID-19 pandemic and its impacts

No Comments

No Known Activations