INDEX

Explanations

database column names

This neuron fires on string literals used as arguments in method calls (e.g. the quoted column‐name or query strings passed inside parentheses).

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

-1.45

an

-1.36

 with

-1.34

for

-1.32

to

-1.26

no

-1.16

on

-1.13

 this

-1.12

in

-1.10

not

-1.05

POSITIVE LOGITS

 applau

1.45

 restant

1.30

︕

1.25

 poliuret

1.24

 feroit

1.23

鷽

1.22

 couv

1.20

 kompres

1.19

 aident

1.17

 continuant

1.16

Activations Density 0.002%