INDEX

Explanations

UV spectroscopy

The neuron strongly activates on the final substantive word just before a sentence or segment boundary.

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

ณฑ

0.77

%%%%%%%%%%%%%%%%

0.74

>>;

0.74

Const

0.73

拳

0.72

>>>

0.70

 един

0.69

Missense

0.68

Overwrite

0.68

Transcription

0.67

POSITIVE LOGITS

ien

0.87

ievable

0.79

iyat

0.77

 rebounds

0.75

 baseless

0.74

ွမ်း

0.74

ুব

0.73

iously

0.73

 Asian

0.73

դ

0.72

Activations Density 0.000%