INDEX

Explanations

unclear, the neuron activates on the word "generality" and the letter "g" in different contexts

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 besides

-0.61

 ſeveral

-0.60

 miſ

-0.58

 attesa

-0.58

besides

-0.58

 zelve

-0.55

ICAGO

-0.53

 Monfieur

-0.51

 various

-0.50

 Beſ

-0.50

POSITIVE LOGITS

 '\\;'

0.85

 generality

0.84

ftagPool

0.79

MigrationBuilder

0.77

تقاوى

0.77

}}">

0.77

+:+

0.76

]")]

0.73

}';

0.71

 Vikipedi

0.70

Activations Density 0.000%