INDEX

Explanations

linker peptide, DNA linker, salt, dup

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

technical terms related to data linkage and connection points (salt, iv, linker, duplicate).

oai_token-act-pair · claude-3-7-sonnet-20250219

Triggered by @neilrathi

The neuron flags domain-specific parameter/keyword tokens—i.e. technical jargon names (like “salt,” “iv,” “dup,” “linker,” “NaNs,” etc.) that represent configuration parameters or key variables.

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

Negative Logits

are

-2.16

怍

-2.09

 hermosas

-2.05

 maravillosas

-2.03

ve

-1.94

 fascinated

-1.93

푙

-1.88

廕

-1.88

 defining

-1.87

 variety

-1.85

POSITIVE LOGITS

 gustaMe

2.19

—

2.06

 untuk

1.95

—"

1.92

方面的

1.86

 для

1.79

ごとの

1.73

 étudi

1.70

เพื่อ

1.70

 crème

1.69

Activations Density 0.003%

linker peptide, DNA linker, salt, dup

technical terms related to data linkage and connection points (salt, iv, linker, duplicate).

The neuron flags domain-specific parameter/keyword tokens—i.e. technical jargon names (like “salt,” “iv,” “dup,” “linker,” “NaNs,” etc.) that represent configuration parameters or key variables.

No Known Activations

linker peptide, DNA linker, salt, dup

technical terms related to data linkage and connection points (salt, iv, linker, duplicate).

The neuron flags domain-specific parameter/keyword tokens—i.e. technical jargon names (like “salt,” “iv,” “dup,” “linker,” “NaNs,” etc.) that represent configuration parameters or key variables.

No Known Activations