INDEX

Explanations

negation or absence

The neuron detects subject/agent words—pronouns and demonstrative tokens that mark who or what the sentence is about (e.g., you, they, someone, this).

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 ofta

0.42

often

0.39

Often

0.38

 vaak

0.38

 souvent

0.38

 portata

0.37

 заку

0.37

 जानकर

0.36

 часто

0.36

 często

0.36

POSITIVE LOGITS

 नहीं

1.03

 نہیں

0.94

 ਨਹੀਂ

0.92

 नही

0.88

 olmayan

0.87

くない

0.83

 less

0.82

 weniger

0.81

 LESS

0.81

NOT

0.81

Activations Density 0.089%