INDEX

Explanations

uses of the pronoun "I" in quotes or speech

oai_token-act-pair · gemini-2.0-flash

first-person statement indicators

np_token-act-pair-logits · gpt-4o-mini

I

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AccessorTable

-0.88

脚注の使い方

-0.87

DockStyle

-0.87

MessageTagHelper

-0.87

 createState

-0.86

MessageOf

-0.79

RegistryLite

-0.79

adaptiveStyles

-0.79

 BoxFit

-0.78

 SwitchCompat

-0.77

POSITIVE LOGITS

 tell

0.50

othelioma

0.48

 think

0.45

funeralhome

0.44

 pikir

0.44

not

0.44

fus

0.43

Yan

0.43

Activations Density 0.481%

uses of the pronoun "I" in quotes or speech

first-person statement indicators

I

No Comments

No Known Activations