INDEX

Explanations

This neuron activates on isolated alphanumeric table or list markers (e.g. single letters or numbers used as row or item labels).

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

Quantitation and Activation

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

empty lines or whitespace between sections of text.

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

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_22/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

ถ

-1.00

メルカリ

-1.00

;//

-0.98

ifié

-0.95

 Kullan

-0.94

 ſer

-0.94

 sert

-0.93

 rése

-0.93

тет

-0.93

breit

-0.93

POSITIVE LOGITS

 where

1.15

 those

1.00

 there

0.96

 with

0.96

↵↵

0.93

 roughly

0.88

 while

0.88

 playing

0.84

quake

0.83

 more

0.82

Activations Density 0.000%

This neuron activates on isolated alphanumeric table or list markers (e.g. single letters or numbers used as row or item labels).

Quantitation and Activation

empty lines or whitespace between sections of text.

No Comments

No Known Activations

This neuron activates on isolated alphanumeric table or list markers (e.g. single letters or numbers used as row or item labels).

Quantitation and Activation

empty lines or whitespace between sections of text.

No Comments

No Known Activations