INDEX

Explanations

cater to different budgets

This neuron fires on the markers of quoted dialogue—especially opening quotation marks and the adjacent words that begin a spoken utterance.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

BUT

1.11

 HOWEVER

1.10

BUT

1.05

但是

0.99

 但是

0.94

 परन्तु

0.94

只能

0.91

 फक्त

0.90

しかし

0.89

 ONLY

0.86

POSITIVE LOGITS

 willingness

0.82

 düzey

0.82

 recept

0.81

 disposition

0.80

 congenial

0.78

 dispositions

0.77

 discretionary

0.76

 willing

0.74

 typically

0.73

 customarily

0.72

Activations Density 0.081%