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

    Neuronpedia

    INDEX
    Explanations

    references to the term "ore" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LabelTagHelper
    -0.68
    Nuorodos
    -0.60
    ising
    -0.57
     Harg
    -0.57
    ArrowToggle
    -0.57
    HomeAsUpEnabled
    -0.56
     habido
    -0.55
    angsaan
    -0.54
     koska
    -0.51
     Farrar
    -0.51
    POSITIVE LOGITS
    ore
    2.63
    ORE
    2.12
    Ore
    1.22
    oré
    1.18
    ores
    1.16
     ORE
    1.16
     ore
    1.15
    ORES
    1.07
    orei
    1.06
    oreo
    1.04
    Act Density 0.063%

    No Known Activations