INDEX

Explanations

names starting with edel, eden, edin

The neuron strongly activates on any token containing the letter sequence “edi.”

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

LING

-0.85

րի

-0.81

 jantar

-0.78

DHCP

-0.78

În

-0.78

نر

-0.77

 corazón

-0.77

Enumerated

-0.76

duced

-0.74

砰

-0.74

POSITIVE LOGITS

繁

0.77

 clues

0.69

abba

0.66

india

0.66

 clue

0.66

man

0.65

 worry

0.65

}^{-\

0.64

Mug

0.63

Billie

0.63

Activations Density 0.024%