INDEX

Explanations

place names and organizations

The neuron strongly activates on numeric tokens—years, section or figure numbers, and other digit‐based references.

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

-2.11

-1.63

for

-1.59

-1.51

 where

-1.47

if

-1.44

 woman

-1.41

 discernible

-1.40

 Männern

-1.36

褔

-1.34

POSITIVE LOGITS

quelize

1.75

of

1.68

 één

1.67

1.61

ၞ

1.59

brtc

1.56

llten

1.56

ixante

1.55

Autoritní

1.55

*/

1.55

Activations Density 0.070%