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

    Neuronpedia

    INDEX
    Explanations

    repeated or recurring phrases and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ou

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     оригіналу
    -0.59
    dataProvider
    -0.55
    potranspiration
    -0.51
    AnimationsModule
    -0.48
     Umwel
    -0.48
     estekak
    -0.47
     setPrice
    -0.47
     tempio
    -0.47
    Adrian
    -0.47
     pinulongan
    -0.47
    POSITIVE LOGITS
     съ
    1.94
     Съ
    1.42
    Съ
    1.42
    съ
    1.07
     Со
    0.77
    Со
    0.60
     съем
    0.55
     conci
    0.54
     σύ
    0.50
    Ъ
    0.50
    Act Density 0.002%

    No Known Activations