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

    Neuronpedia

    INDEX
    Explanations

    references to the "Holy Roman Empire" and the term "Holy" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.63
    endpush
    -0.57
    tagHelperRunner
    -0.54
    AddTagHelper
    -0.53
     resourceCulture
    -0.49
     ujednoznacz
    -0.47
     يتيمه
    -0.46
    pieler
    -0.46
    atschappij
    -0.45
    <?
    -0.45
    POSITIVE LOGITS
     Trinity
    0.56
     grail
    0.52
     trinity
    0.50
    trinity
    0.47
     Moly
    0.47
     moly
    0.47
    Trinity
    0.46
     cow
    0.45
     Ghost
    0.44
     mackerel
    0.43
    Act Density 0.196%

    No Known Activations