INDEX

Explanations

mannose and man-ending words

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

The neuron detects the word "man" and its derivatives, particularly in chemical/biological contexts like "mannose".

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @neilrathi

The neuron is triggered by occurrences of the substring “man” (e.g. the token “Man” or “man” in words like mannose).

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

If

-2.14

’

-1.78

ufnahme

-1.73

sistors

-1.73

 ولی

-1.66

彇

-1.57

 стороне

-1.56

henden

-1.55

讃

-1.55

在她

-1.54

POSITIVE LOGITS

</h2>

3.08

</sup>

2.27

//};

2.25

发生的

2.09

荜

2.08

");

2.05

佧

2.00

抟

1.95

")

1.95

//});

1.94

Activations Density 0.001%

mannose and man-ending words

The neuron detects the word "man" and its derivatives, particularly in chemical/biological contexts like "mannose".

The neuron is triggered by occurrences of the substring “man” (e.g. the token “Man” or “man” in words like mannose).

No Comments

No Known Activations

mannose and man-ending words

The neuron detects the word "man" and its derivatives, particularly in chemical/biological contexts like "mannose".

The neuron is triggered by occurrences of the substring “man” (e.g. the token “Man” or “man” in words like mannose).

No Comments

No Known Activations