INDEX

Explanations

references to murine or related rodent models in scientific contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fered

-1.40

 disclose

-1.38

oyd

-1.31

rugu

-1.30

 ComissÃ£o

-1.27

qc

-1.27

ublic

-1.27

 Yugoslav

-1.25

 solved

-1.25

 Czech

-1.25

POSITIVE LOGITS

¿½

1.94

 hearts

1.80

 weddings

1.75

Īĺ

1.58

 heart

1.46

 needs

1.41

º

1.38

 juices

1.37

¢

1.36

ilent

1.36

Activations Density 0.005%

references to murine or related rodent models in scientific contexts

No Comments

No Known Activations