Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    syntactic structures and punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     either
    -0.19
    ä¼ı
    -0.14
     itself
    -0.14
    inness
    -0.14
     Either
    -0.14
     indeed
    -0.14
    either
    -0.14
     alike
    -0.13
    еб
    -0.13
    nt
    -0.13
    POSITIVE LOGITS
     //
    0.54
    //
    0.40
     <!--
    0.32
     //↵
    0.25
    <!--
    0.23
    ,//
    0.23
     ///
    0.23
     #
    0.22
     {/*
    0.21
     âĢ¢
    0.20
    Act Density 0.373%

    No Known Activations