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

    Neuronpedia

    INDEX
    Explanations

    tokens that represent structured data formats or programming commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.86
    OGND
    -0.82
    AddTagHelper
    -0.76
     kasarigan
    -0.75
    LookAnd
    -0.74
     autorytatywna
    -0.71
    richTextPanel
    -0.68
    ьаж
    -0.65
     <<<<<<<<<<<<<<
    -0.65
    Diweddarwch
    -0.64
    POSITIVE LOGITS
     also
    0.59
     elsewhere
    0.48
     även
    0.48
     ayrıca
    0.48
     other
    0.48
     lainnya
    0.47
     weiteren
    0.47
     остальных
    0.46
     همچنین
    0.46
     later
    0.45
    Act Density 3.287%

    No Known Activations