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

    Neuronpedia

    INDEX
    Explanations

    phrases that express necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amento
    -0.17
    ysl
    -0.17
    aska
    -0.17
    rescia
    -0.15
    cad
    -0.15
    ascal
    -0.15
    oldt
    -0.15
     yar
    -0.15
    dum
    -0.15
    Salir
    -0.14
    POSITIVE LOGITS
     dele
    0.17
    lef
    0.16
    icast
    0.14
    UnitTest
    0.14
     Dann
    0.14
    ipped
    0.14
     Tee
    0.13
    ικη
    0.13
     ì²ĺ
    0.13
     unint
    0.13
    Act Density 0.061%

    No Known Activations