INDEX

Explanations

references to financial crimes and fraudulent activities

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Réponses

-0.74

abestanden

-0.69

 ModelExpression

-0.65

 estekak

-0.63

rítica

-0.59

Портал

-0.59

رشف

-0.58

 <<<<<<<<<<<<<<

-0.57

 canv

-0.56

المكان

-0.55

POSITIVE LOGITS

fraud

0.64

 fraud

0.59

 defraud

0.56

 scam

0.56

 Fraud

0.54

 Liar

0.52

 scammed

0.51

 fraude

0.50

Scam

0.50

ActionCreators

0.49

Activations Density 0.005%

references to financial crimes and fraudulent activities

No Comments

No Known Activations