INDEX

Explanations

The neuron activates on verbs that describe granting bonuses or effects (e.g. “gives” or “give”) in item or ability descriptions.

bonus and percentage effects

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

%;

-1.24

 "'");

-1.04

estima

-1.03

 удовлет

-1.02

 веке

-1.01

 glyphicon

-1.00

[]}

-0.97

〉

-0.97

".$

-0.96

 rozwią

-0.96

POSITIVE LOGITS

you

1.91

 effects

1.63

 your

1.45

 effect

1.32

 increase

1.30

影响

1.20

랐

1.20

folia

1.20

 affecting

1.15

 factors

1.13

Activations Density 0.015%