INDEX

Explanations

guide: common methods, explanations, examples

The neuron is strongly activated by numeric tokens—especially decimal‐formatted numbers.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

ल्ल्या

0.64

 سبتمبر

0.61

entretien

0.61

jš

0.60

 پیشنهاد

0.59

stricken

0.59

 सप्टेंबर

0.59

ⓡ

0.59

 сент

0.58

 chủ

0.57

POSITIVE LOGITS

Warning

0.61

See

0.59

 getName

0.58

 Warning

0.55

 stresses

0.52

Warn

0.52

 warning

0.51

see

0.50

Stress

0.50

 WARNING

0.50

Activations Density 0.052%