INDEX

Explanations

platform

This neuron fires strongly on the very first token of each new text segment, effectively marking segment or document boundaries.

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

𝙚

0.88

蜷

0.83

नून

0.79

ເນ

0.77

يو

0.74

சி

0.72

oxides

0.72

то

0.71

イギリス

0.71

தெ

0.71

POSITIVE LOGITS

?)

0.83

 titulo

0.79

 föret

0.78

});

0.77

 tão

0.77

})$.

0.76

 função

0.75

}).

0.75

či

0.74

 telefone

0.74

Activations Density 0.001%