INDEX

Explanations

TDD, world, myself

The neuron strongly activates on reflexive pronouns—words ending in “self” or “selves” (e.g. himself, myself, itself, themselves).

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

-1.81

When

-1.80

 '-':

-1.68

 relativo

-1.63

 terremoto

-1.61

 когда

-1.59

dicionado

-1.55

 với

-1.55

大家好

-1.55

ędzynarod

-1.52

POSITIVE LOGITS

奔驰

1.64

 -----

1.57

an

1.55

for

1.53

.''

1.48

他能

1.45

 anaknya

1.44

 tokoh

1.42

belts

1.41

鸶

1.41

Activations Density 0.037%