INDEX

Explanations

throwing and tossing something

The neuron activates on verbs describing the act of propelling or tossing objects (e.g. “toss,” “throwing,” “dropped”).

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

 that

-1.54

—

-1.30

 where

-1.27

how

-1.27

see

-1.26

new

-1.23

 This

-1.23

↵↵↵

-1.22

 available

-1.21

 это

-1.20

POSITIVE LOGITS

呗

1.32

ッフェ

1.29

IZONT

1.29

odotus

1.27

 plupart

1.24

 مسلسل

1.23

⫽

1.21



1.18

好像是

1.18

meneu

1.16

Activations Density 0.030%