INDEX

Explanations

aws amazon services Kinesis SES guide

np_acts-logits-general · gemini-2.5-flash-lite

AWS service names and API-related terms in technical documentation and code.

oai_token-act-pair · claude-4-5-sonnet Triggered by @bfgcn7frf5

The neuron fires on AWS IAM–style policy and role definitions, spotting tokens like “AWS,” “role,” ARNs, and “AssumeRole.”

oai_token-act-pair · o4-mini Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_10/width_131k

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Overwatch

-1.34

 alça

-1.30

Eminem

-1.24

Hotline

-1.15

 alſo

-1.15

 bật

-1.11

 aktivi

-1.10

ਤੇ

-1.07

 verdaderos

-1.06

 temel

-1.05

POSITIVE LOGITS

 Amazon

1.27

AWS

1.23

</h2>

1.16

ferred

1.13

 geheel

0.99

などなど

0.96

 EdgeInsets

0.96

use

0.95

قه

0.95

給你

0.95

Activations Density 0.159%

aws amazon services Kinesis SES guide

AWS service names and API-related terms in technical documentation and code.

The neuron fires on AWS IAM–style policy and role definitions, spotting tokens like “AWS,” “role,” ARNs, and “AssumeRole.”

No Comments

No Known Activations

aws amazon services Kinesis SES guide

AWS service names and API-related terms in technical documentation and code.

The neuron fires on AWS IAM–style policy and role definitions, spotting tokens like “AWS,” “role,” ARNs, and “AssumeRole.”

No Comments

No Known Activations